Automation and AI Developer

Thomson Reuters is a “Great Place to Work® certified Organization. We are looking for a skilled Automation & AI Developer to design, build, and own intelligent solutions from concept to production. In this role, you will work on agentic AI implementations using AWS AgentCore and LangGraph, contributing to both rapid POCs and live systems. About the Role In this role as an Automation & AI Developer, you will: Agentic AI Development Implement LangGraph agentic workflows on AWS AgentCore — state graphs, tool orchestration, conditional routing, error recovery. Build custom RAG pipelines end-to-end: chunking strategy, embeddings, vector retrieval, accuracy evaluation. Contribute to rapid POC delivery alongside the Architect and Lead. Write production-grade Python with FastAPI, Pydantic, testing, and proper error handling. Use AI coding tools (Claude Code, GitHub Copilot, Cursor, Cline) to accelerate builds. Own and fix all generated code in production. Low Code & Automation Build Low Code automations using Microsoft Copilot Studio and Power Automate when use case and bandwidth allow. Understand Pro Code vs Low Code trade-offs — flag where Low Code is the better fit. Stay current on Low Code platform capabilities as they expand rapidly. Production Ownership & Collaboration Own assigned components in production — monitor, debug, optimise, iterate. Debug agent failures independently: context issues, tool errors, hallucination, retrieval degradation. Collaborate with the Lead on architecture translation and implementation planning. Mentor Associate Developers through code reviews and pair programming. Work Mode: Hybrid - 3 days from office. Shift Timing: 1pm IST to 10pm IST About You You’re a fit for the role of Automation & AI Developer, if your background includes: Must Have: Experience — 3–5 years total; 1–2 years GenAI/LLM; 6–12 months LangGraph; 2–3 projects with working code. LangGraph — State graphs, conditional routing, checkpointing — primary framework, non-negotiable. LangChain — Chains, memory, custom tools — solid foundational knowledge. AWS AgentCore — Hands-on preferred; strong LangGraph depth with ramp path acceptable. AWS Bedrock — Model invocation, knowledge bases, guardrails. Database & AI Data Access — SQL proficiency, NL-to-SQL, LLM-powered query and insight patterns. Snowflake a plus. RAG Pipelines — End-to-end: chunking, embeddings, retrieval, evaluation. Vector Databases — Pinecone, ChromaDB, OpenSearch, or FAISS — hands-on with at least one. Python — Production-quality — type hints, async/await, FastAPI, Pydantic. Multi-Model — OpenAI, Claude, Gemini, Llama — understand trade-offs across providers. Pro Code vs Low Code — Copilot Studio and Power Automate — build when use case fits. AI Development Tools — Claude Code, GitHub Copilot, Cursor, or Cline — accelerate delivery; own and fix all generated code. Good to Have: AWS AgentCore Deep — Runtime, Memory, Tools Gateway hands-on. MCP / A2A — Server/client implementation or protocol awareness. Enterprise Integration — SAP HANA, Salesforce connectors. Document Intelligence — OCR, layout-aware chunking. Evaluation Frameworks — RAGAS, Promptfoo, DeepEval Certifications — AWS, GCP, or Azure AI/ML. #LI-GS2 What’s in it For You? Hybrid Work Model: We’ve adopted a flexible hybrid working environment (2-3 days a week in the office depending on the role) for our office-based roles while delivering a seamless experience that is digitally and physically connected. Flexibility & Work-Life Balance: Flex My Way is a set of supportive workplace policies designed to help manage personal and professional responsibilities, whether caring for family, giving back to the community, or finding time to refresh and reset. This builds upon our flexible work arrangements, including work from anywhere for up to 8 weeks per year, empowering employees to achieve a better work-life balance. Career Development and Growth: By fostering a culture of co ... (truncated, view full listing at source)