Senior AI Engineer
LevelSeniorExperience12+ years software engineering; 2+ years building LLM-powered applications in productionMust havePython (production-grade); LLM application development; agentic AI / agent frameworks; RAG pipeline implementation; AI evaluation and testingMust haveMCP or equivalent tool-use protocol experience; prompt engineering at production scaleNice to haveTypeScript; Neo4j or graph databases; SAP AI Core or equivalent enterprise AI runtime; financial services domain knowledge
Hands-on builder first. This is not an architecture-only role the role is expected to write production code alongside the team, lead by doing, and be the most technically capable person on the Agent Skills Team.

- LLM Foundations deep understanding of transformer behaviour, tokenization, context windows, sampling controls, hallucination patterns, and latency/cost tradeoffs; uses this knowledge to make sound model selection and prompt architecture decisions
- Production-grade prompt engineering task decomposition, system/developer/user prompt layering, reusable templates, guardrails, adversarial robustness testing (jailbreak resistance, edge-case handling), and prompt versioning with experiment tracking and rollback
- AI evaluation & quality engineering designs eval frameworks with metrics covering accuracy, groundedness, safety, latency, and cost; builds automated eval pipelines (LLM-as-judge, golden sets, regression suites); owns observability including trace logs, failure clustering, and drift detection
- Agentic AI & A2A orchestration hands-on implementation of agent orchestration, multi-step reasoning, ReAct / plan-and-execute; designs A2A patterns (agent roles, delegation, handoff protocols, state boundaries) and multi-agent governance (permissions,



execution constraints, escalation paths)
- MCP (Model Context Protocol) builds and owns common MCP servers; defines tool schemas, capability discovery, and interface contracts; implements tool reliability patterns (input/output validation, fallback strategies, circuit breakers)
- RAG pipeline implementation builds chunking, embedding, and retrieval pipelines end-to-end; tunes retrieval quality through code; owns knowledge base ingestion and refresh strategy
- Software engineering & MLOps backbone Python/TypeScript proficiency; CI/CD for AI systems with eval gates before deployment; cost/performance optimisation (caching, batching, model routing); data security (PII handling, secrets management, audit logging)
- Cross-team technical leadership Leads by example in code quality and AI engineering practices; can explain model behaviour and limitations to non-technical stakeholders

AI Engineer
LevelMid to SeniorExperience8+ years software engineering; 1+ years working with LLMs or AI systems in productionMust havePython; LLM API integration; prompt engineering basics; RAG implementation; REST API developmentMust haveAgent framework experience (LangChain, LangGraph, or equivalent); automated testing for AI outputsNice to haveTypeScript; MCP; vector store experience; Neo4j; CI/CD pipeline experience; financial services domain knowledge





- LLM Foundations working knowledge of transformer behaviour, context windows, sampling controls, and model limitations; applies this to write prompts and integrations that behave predictably in production
- Prompt engineering implements production-grade prompts using system/developer/user layering, reusable templates, and structured outputs; applies robustness testing for adversarial inputs and edge cases; tracks prompt versions and supports A/B releases
- LLM evaluation builds automated eval pipelines (LLM-as-judge, golden test sets, regression suites); writes domain-specific test cases; contributes to observability tooling (trace logs, failure clustering)
- Agentic AI & A2A basics implements agent workflows (planning loops, retries, timeout handling, idempotent tool calls); understands A2A handoff and delegation patterns; applies tool reliability practices (fallbacks, circuit breakers, input/output validation)
- MCP (Model Context Protocol) implements and consumes MCP servers and tools; works within common MCP contracts defined by the AI Lead; extends with use-case-specific tooling
- RAG & knowledge base management builds and maintains embedding pipelines, vector store integrations, and retrieval logic; owns ingestion refresh and embedding quality monitoring
- Software engineering & MLOps Python (and TypeScript where needed); REST API development; CI/CD for AI with eval gates; cost/performance awareness (caching, batching); data security practices (PII handling, secrets management, audit logging)
- Inner-source contribution documents patterns clearly for reuse; participates in PR reviews; maintains pattern library with the discipline of a shared codebase owner

📌 Artificial Intelligence Engineer (Hyderabad)
🏢 Abacus Service
📍 Hyderabad