Posted today · be early
Generative AI Engineer
Mactores
IndiaremotePosted today
Skill Required
Generative-AI-EngineeringAI-EngineeringMachine-Learning-EngineeringData-Engineering-And-Data-ScienceEngineeringGenerative-AI-EngineerGenerative-AI-DeveloperGenerative-AI-SpecialistAI EngineerGenerative AIAIsoftware engineeringDesign PatternsObservabilityTypeScriptsimilar)MLflowRedshiftDynamoDBbuildingGolangwrittenTestNGPythondesignISO 27001C++.NETKafkaCI/CDJavaRustRAGFulltime
Key highlights
- Primary must-have: Proven experience shipping production (not POC/demo) agentic AI systems on AWS
- Role is a forward-deployed engineer position embedding with customer teams to own end-to-end delivery from discovery to production cutover
- Proprietary Aedeon agent platform automates 60–70% of routine engagement work for modernization projects
- Indicative experience requirement: 3–10 years of engineering experience, with hands-on agentic AI/GenAI as current primary focus
- Non-negotiable requirement: Excellent English verbal and written communication skills
- Preferred qualifications include delivery experience in regulated verticals or relevant AWS certifications
Role overview
Mactores is an agent-native AWS modernization firm focused on delivering production-ready modernization and agentic AI systems, rather than stalled pilot projects or over-budget engagements that are common in the industry. The firm uses its proprietary Aedeon agent platform to automate 60–70% of routine engagement work including discovery, dependency mapping, validation, and test generation, while forward-deployed engineers (FDEs) handle high-judgment tasks including architecture design, refactoring trade-offs, and production cutover, with personal commitment to delivery timelines agreed to in client contracts. FDEs embed directly with customer engineering teams to own end-to-end outcomes for AWS modernization, data platform modernization, application and database modernization, and AI agent implementation for applications and business processes, working across regulated verticals where applicable.
Responsibilities
- Deliver production agentic AI systems and AWS modernization engagements on committed dates across three pillars: Data Platform Modernization, Application & Database Modernization, and AI Agents for Apps
- Build and productionize AI agents, orchestration, retrieval pipelines, evaluation harnesses, and observability running against real customer data, not demo data
- Convert existing products into agents: expose product functionality as callable tools for agent-to-agent composition, or replace form-and-click UX with agent-native, intent-driven interfaces
- Convert existing Business processes into agents: expose process functionality as callable tools for agent-to-agent composition, or replace form-and-click UX with agent-native, intent-driven interfaces
- Embed directly with customer engineering teams. Run architecture sessions, defend design decisions, and align stakeholders from VP Engineering to CTO
- Make agent decisions traceable and defensible, validation runs in parallel with live workloads, and outputs hold up to internal audit and regulators (HIPAA, PCI-DSS, FSI-grade governance where the vertical demands it)
- Feed field experience back into the platform and practice: your deployment patterns, integration playbooks, and edge cases shape how we deliver
- Absorb high-judgment decision-making for engagements including target architecture design, refactoring trade-offs, model selection, cutover strategy, and all decisions the Aedeon agent platform cannot make
Requirements
- Excellent verbal and written English communication skills (non-negotiable), with ability to present architecture to customer CTOs, write audit-ready documentation, and defend judgment calls in stakeholder meetings
- Proven experience shipping production agentic AI systems on AWS (not POCs, notebooks, or demos — systems running in production for real users, with ability to discuss shipped work, decisions made, and issues encountered) — this is the primary qualification
- Deep understanding of agentic architecture, including ability to design agent systems from first principles and explain component purpose, with expertise in: agent design patterns (single-agent vs. multi-agent systems, supervisor/orchestrator patterns, hierarchical agent topologies, planner–executor separation, and applicable use cases for each); orchestration (building and operating orchestrator agents that decompose tasks, route work to specialist agents or tools, and manage state across multi-step workflows using LangGraph, Strands Agents, CrewAI, or equivalent); memory (short-term/working memory for context management and conversation state, long-term memory for episodic and semantic stores, vector- and graph-backed retrieval, and production trade-offs of each); reflection and self-correction (critique loops, self-evaluation, retry-with-feedback patterns, and evaluation harnesses that catch agent failures before customers do); tool use and function calling (schema design, tool-selection reliability, error handling, and agent-to-agent composition); RAG and retrieval pipelines (chunking, embedding, hybrid retrieval, reranking, and grounding agent decisions in customer data)
- Strong AWS production experience, including Amazon Bedrock and AWS AI services, plus core platform services (Lambda, API Gateway, DynamoDB, RDS/Aurora, Glue, EMR, Redshift, Kinesis, or similar depending on specialization)
- Solid software engineering fundamentals including Python, TypeScript, CI/CD, infrastructure-as-code, and test-driven development discipline
- Indicative experience level: 3–10 years in engineering roles, with agentic AI / GenAI as current primary work focus (demonstrated agent-native expertise is prioritized over total tenure, with 3–4 years of hands-on agentic AI work typically outperforming 12 years of generalist experience)
Nice to have
- US English verbal and written fluency
- Delivery experience in one or more of Mactores' verticals: Financial Services, Healthcare & Life Sciences, Internet & Software, Manufacturing, or Telco/Media/Entertainment/Gaming/Sports
- Model tuning and fine-tuning expertise, including systematic prompt engineering and optimization; parameter-efficient fine-tuning (LoRA/QLoRA or similar); instruction tuning; working knowledge of RLHF/DPO; sound judgment on when to fine-tune vs. prompt vs. RAG; and evaluation of tuned models against baselines (fine-tuning experience on Amazon Bedrock or SageMaker is a plus)
- Experience with compliance-sensitive AI systems (HIPAA, PCI-DSS, SOC 2, data residency)
- Knowledge graph, code-analysis (AST), or CDC/streaming experience (Debezium, Kafka/MSK)
- Solid software engineering fundamentals in Java, C++, Go Lang, .Net, or Rust
- Prior customer-facing consulting or forward-deployed experience
- AWS certifications (Solutions Architect Professional, Machine Learning Specialty, or Data Analytics)
- Experience with data or application modernization (database migration, legacy refactoring, data platform builds)
Benefits
- Personal ownership of end-to-end delivery outcomes (architecture, judgment, and production cutover) rather than individual tickets
- Agent-native work model from day one, using the proprietary Aedeon platform for delivery rather than building around limited tooling
- Focus on shipping production systems with engagements measured in weeks to production, no stalled or archived pilot projects
- Opportunity to shape the proprietary Aedeon platform roadmap via field delivery experience, with platform growth expanding the scope of work you can deliver
Additional details
- Mactores is the agent-native AWS modernization firm; most traditional modernization work stalls in pilots, slips a year, or lands at three times the budget, and the firm exists to ship production systems running, legacy retired, and outcomes measured
- The Aedeon agent platform, built by Mactores' founders' sister company, absorbs 60–70% of routine engagement work including discovery, dependency mapping, validation, and test generation that traditional consulting bills human hours against
- This role is not a staff-augmentation seat and not an advisory role; the core focus is on shipping production systems
- Mactores' 10 Core Leadership Principles guiding work culture: Be one step ahead; Deliver the best; Be bold; Pay attention to the detail; Enjoy the challenge; Be curious and take action; Take leadership; Own it; Deliver value; Be collaborative. Additional work culture details are available via a provided link
- The recruitment process for the role has three distinct stages: 1) Pre-Employment Assessment (series of evaluations of technical proficiency and role suitability); 2) Managerial Interview (multiple 30-minute to 1-hour discussions with the hiring manager covering technical skills, hands-on experience, leadership potential, and communication); 3) HR Discussion (30-minute session to discuss the offer and next steps with an HR team member)
- Mactores provides equal employment opportunities and does not discriminate based on race, religion, gender, national origin, age, disability, marital status, military status, genetic information, or any other category protected by federal, state, and local laws, across all employment practices including recruitment, compensation, promotions, transfers, disciplinary action, layoff, training, and social and recreational programs
- Applicants are encouraged to answer as many application questions as possible to accelerate the hiring process
- The role was originally posted on Himalayas