We're looking for a Senior AI Engineer to help build the next generation of AI-native products at Awin. You will own real problems end-to-end, make architecture decisions the team builds on and balance technical depth with the realities of shipping software to customers.
## What You'll Do
- Design, build and operate customer-facing AI features end-to-end, from conversational experiences to intelligent automation
- Architect agent-based systems: multi-step reasoning, tool execution, sub-agent orchestration, state management and streaming, structured outputs, persistent memory and human-in-the-loop approval flows
- Decide how the system grounds, retrieves and constructs context
- Pick the right pattern (retrieval, structured tools, agentic flows) for each problem and be able to defend the choice
- Treat prompt and context engineering as first-class engineering work
- Own AI quality. Build evaluation datasets, regression tests for prompts and agents and the debugging discipline needed to get to root cause across model outputs, retrieval and tool calls
- Make AI production-ready: observability, tracing, reliability, cost, latency and the safety controls that protect against hallucination, prompt injection and context leakage
- Make and explain the trade-offs between accuracy, latency, cost and safety within engineering and product partners
- Turn ambiguous product ideas into concrete technical designs and influence roadmap with what the technology actually makes possible
- Mentor engineers around you, contribute to design reviews and our hiring bar and raise the standard for what production-ready AI means inside the team
## What You'll Bring
- 8+ years of professional software engineering experience, with a track record of shipping production systems
- Strong Python and backend system design
- Real, hands-on experience building and running production LLM-based systems not just prototypes
- Deep experience with agent-based architectures using frameworks such as LangGraph, Deep Agents or equivalents with multi-step reasoning, tool use, sub-agent orchestration, state and streaming
- Strong working knowledge of retrieval and context construction (RAG, embeddings, chunking, ranking) and good judgement about when to use those patterns inside an agentic system
- A solid track record of evaluating and debugging AI systems: structured evals, regression tests and tracing or observability with tools such as LangSmith or similar
- Familiarity with emerging agent orchestration standards (MCP or similar). Experience with vector databases and hybrid retrieval
- A clear understanding of LLM failure modes like prompt injection, content safety, context leakage and how to mitigate them in real systems
- Strong fundamentals in distributed systems, API design and cloud-native architectures on AWS (ECS, Lambda, S3, API Gateway)
- Confident with PostgreSQL, Redis, Docker and modern CI/CD pipelines like GitHub Actions
- A collaborative engineer who's comfortable working in a Scrum team alongside Product, UX and cross functional teams