Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store
Ellkay SoftwarePosted 18 days ago

Senior AI Engineer - LLM & Agentic Workflows

IndiaSeniorRemote or on-siteFull-time
Who we'd reach at Ellkay SoftwareFound and reached by Power Apply
Best leadHiring manager

Leads the team this role joins

Recruiter

In-house, owns the opening

Posted this job

Put the opening up

Power Apply

From your own Gmail and LinkedIn.

About the role

This is a senior AI engineering role building production LLM applications and agent workflows, open across India, in multiple locations or remotely. It suits engineers with at least five years in software or AI engineering who have built backend services and retrieval-based LLM systems. The work covers retrieval-augmented generation, tool calling and approval checkpoints for implementation help, migration operations and archive access. Ellkay Software is a data management partner to healthcare organisations, including laboratories, hospitals, health systems, health IT vendors and health plans.

What you’ll do

  • Build RAG and tool-calling workflows for implementation help, connector discovery, error explanation and guided migrations.
  • Assemble context from approved documentation, run status, mapping metadata and evidence.
  • Implement MCP clients and tool integrations, with thin adapters over platform contracts.
  • Handle async request IDs, retries, timeouts and duplicate action prevention.
  • Build permission-aware retrieval, approval checkpoints, prompt-injection defenses and bounded tool use.
  • Capture agent traces and user feedback, and write regression tests for prompts, tool selection and retrieval.
  • Improve retrieval and context assembly using measured failures.
  • Work with data platform engineers, product engineers, clinical and data specialists, QA and security teams.

What they’re looking for

  • At least five years in software or AI engineering, including production LLM applications and backend services.
  • Strong Python, REST APIs, asynchronous programming, data handling, testing and production debugging.
  • Hands-on experience with RAG, hybrid and vector search, embeddings, reranking, structured outputs and tool calling.
  • Experience with agent state, timeouts, bounded retries, approval checkpoints and fallbacks.
  • Ability to measure retrieval relevance, groundedness, tool selection, task completion, latency and unit cost.
  • Experience deploying services to a cloud environment.
  • Experience with authorisation-aware retrieval and PHI-safe telemetry.

Nice to have

  • MCP, LangGraph or equivalent agent orchestration.
  • FastAPI.
  • AWS, Docker and Kubernetes.
  • Familiarity with HL7 and FHIR.
  • Enterprise authorisation patterns.

What’s on offer

  • Work from anywhere in India, in multiple locations or remotely.

Skills

Questions about this role

Is this job remote?

The posting lists work anywhere in India, in multiple locations or remotely.

How many years of experience are needed?

At least five years in software or AI engineering, including production LLM applications.

Is healthcare experience required?

The posting asks for PHI-safe telemetry and lists HL7 and FHIR familiarity as preferred.