Posted today · be early
Senior Software Engineer - Chat & Agent Systems
Kantiv (formerly Joist AI)
IndiaremotePosted today
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
- Approximately 4–5 years of professional software engineering experience required.
- Strong proficiency in Python required.
- Hands‑on experience building LLM or agentic applications required.
- Mentor junior developers and guide engineering practices.
- Own technical design and delivery of chat‑team projects.
- Opportunity to shape engineering priorities and standards.
Role overview
We’re looking for a strong software engineer with roughly 4–5 years of experience to play a central role in our chat team. You’ll 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 (required).
- 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.
- Power‑user of agentic coding workflows and ability to use coding agents as engineering tools rather than simple code generators.
- Use coding agents effectively across exploration, planning, implementation, testing, debugging, and review.
- Provide agents with the right context, constraints, and verification steps.
- Critically evaluate generated code for correctness, security, maintainability, and unnecessary complexity.
- Design development workflows that keep engineers accountable for the resulting code.
- Identify repeatable team workflows that can be improved through agents and automation.
- Teach junior developers how to use coding agents effectively without weakening their engineering fundamentals.
- 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; projects have simple designs, well‑defined boundaries, and useful tests; code reviews catch meaningful design and correctness issues early; junior developers receive actionable guidance and grow more independent; the team develops effective and responsible agentic coding practices; production issues become easier to diagnose and resolve; the codebase becomes easier to understand, change, and operate over time.
- Originally posted on Himalayas.
