Senior Software Engineer - Chat & Agent Systems
Kantiv (formerly Joist AI)
IndiaremotePosted 1 month ago
Skill Required
Senior-AI-Agent-EngineerSenior-AI-Software-EngineerSenior-Software-AI-EngineerSenior-Systems-Software-EngineerSenior-AI-EngineerSenior-AI-Software-DeveloperAI-Agent-Systems-EngineerSoftware-EngineerSoftware EngineerSoftware Developersoftware engineeringSystem DesignObservabilityEngineeringR ProgrammingautomationdesigningdebuggingsecuritybuildingwrittenTestNGPythonPytestdesignAPIsandGenerative AIAIFulltime
Key highlights
- Roughly 4–5 years of professional software engineering experience required
- Hands-on experience building LLM or agentic applications is required
- Power user of agentic coding workflows required — understanding how to use coding agents as engineering tools, not simple code generators
- Central role in chat team with technical leadership and mentoring responsibilities
- Must combine strong programming fundamentals with practical experience building agentic systems
- Strong Python proficiency expected, including idiomatic, typed, testable, and maintainable production code
Role overview
We are looking for a strong software engineer with roughly 4–5 years of experience to play a central role in our chat team. You will help shape the team's technical direction, own the system design of day-to-day projects, maintain a high bar for engineering quality, and support junior developers through thoughtful design guidance and code reviews. This is a hands-on role for someone who combines strong programming fundamentals with practical experience building agentic systems.
Responsibilities
- Own the technical design and delivery of chat-team projects.
- Shape engineering priorities, standards, and day-to-day technical decisions.
- Turn product requirements into simple, maintainable system designs.
- Write production Python and remain closely involved in implementation.
- Design clear abstractions that reduce complexity without over-engineering.
- Review pull requests for correctness, maintainability, test coverage, and overall design quality.
- Help junior developers strengthen their programming and system-design judgment.
- Diagnose production issues across application code, agent workflows, prompts, models, data, and infrastructure.
- Improve the reliability, observability, latency, and cost of our chat systems.
- Take initiative in making the team more AI-native by improving how we use coding agents throughout the development lifecycle.
- Mentor other engineers in effective agentic coding workflows, including planning, implementation, testing, debugging, and code review.
Requirements
- Approximately 4–5 years of professional software engineering experience.
- Strong proficiency in Python, including writing idiomatic, typed, testable, and maintainable production code.
- Strong programming fundamentals and consistently sound engineering judgment.
- Experience designing, delivering, and operating production systems.
- An ability to create useful abstractions while keeping systems simple and understandable.
- Strong knowledge of API design, data modeling, concurrency, error handling, and observability.
- Experience writing effective automated tests with tools such as pytest.
- The ability to review code beyond surface-level concerns and explain the reasoning behind suggested changes.
- Experience mentoring junior developers and improving the quality of their work.
- Comfort taking ownership, identifying opportunities, and driving improvements across a team.
- Clear written and verbal communication.
- Hands-on experience building LLM or agentic applications is required. Relevant experience may include: building tool-calling or multi-step workflows using LangGraph or a comparable agent framework; designing conversation state, context management, and execution flows; working with model APIs, structured outputs, retrieval, and grounding; supporting streaming responses and asynchronous execution; evaluating prompts, models, and end-to-end agent behavior; instrumenting and debugging LLM applications with Langfuse, LangSmith, or similar observability platforms; managing the reliability, latency, and cost of production LLM systems.
- The candidate should be a power user of agentic coding workflows and understand how to use coding agents as engineering tools rather than simple code generators.
- Ability to use coding agents effectively across exploration, planning, implementation, testing, debugging, and review.
- Ability to provide agents with the right context, constraints, and verification steps.
- Ability to critically evaluate generated code for correctness, security, maintainability, and unnecessary complexity.
- Ability to design development workflows that keep engineers accountable for the resulting code.
- Ability to identify repeatable team workflows that can be improved through agents and automation.
- Ability to teach junior developers how to use coding agents effectively without weakening their engineering fundamentals.
- Ability to lead practical initiatives that make the team faster and more AI-native.
Additional details
- We do not expect expertise in every named tool. We care about the underlying engineering judgment and the ability to learn or replace frameworks as the ecosystem changes.
- What success looks like: The team makes clearer and more consistent technical decisions.
- What success looks like: Projects have simple designs, well-defined boundaries, and useful tests.
- What success looks like: Code reviews catch meaningful design and correctness issues early.
- What success looks like: Junior developers receive actionable guidance and grow more independent.
- What success looks like: The team develops effective and responsible agentic coding practices.
- What success looks like: Production issues become easier to diagnose and resolve.
- What success looks like: The codebase becomes easier to understand, change, and operate over time.
- Originally posted on Himalayas.