Senior AI / ML Engineer

at Flycatch infotech PVT LTD

Senior AI / ML Engineer

Flycatch infotech PVT LTD

Company

Home

Senior AI / ML Engineer

at Flycatch infotech PVT LTD

Posted by Nidhun K santhosh

8 - 10 yrs

₹8L - ₹10L / yr

Remote only

Skills

Python

FastAPI

Flask

Large Language Models (LLM)

1. Senior AI / ML Engineer

Level: Senior

Experience: 8–10 years

Function: AI / ML Engineering

Role Overview

As Senior AI / ML Engineer, you will own the intelligence layer of the platform — the agent

reasoning, orchestration, and model-integration core that determines how agents are built, how

they reason, and how they act once deployed. You will design the systems that let users

compose multi-step, tool-using agents reliably and at scale.

Key Responsibilities

• Design and build the agent orchestration and reasoning layer — planning, tool calling,

multi-agent coordination, memory, and state management.

• Integrate and abstract multiple LLM providers behind a unified, swappable model layer so

agents are not tied to a single model.

• Build and optimize RAG pipelines, embeddings, vector search, and the memory systems

agents rely on.

• Implement evaluation, guardrails, and observability for agent behavior — accuracy, safety,

latency, and cost.

• Develop the reusable agent primitives, prompt frameworks, and adaptation workflows that

the builder experience is composed from.

• Optimize inference performance, throughput, and cost across the platform's runtime.

• Contribute to the platform's AI Gateway — a unified entry point for routing, rate-limiting,

caching, and managing traffic across multiple models and providers.

• Embed AI Governance into the platform at a high level — model and prompt versioning,

audit trails, usage policies, and responsible-AI controls over how agents are built and run.

Help define AI Security practices — prompt-injection and jailbreak defenses, data privacy,

secrets handling, and safe tool / action execution for deployed agents.

• Work with the full-stack and backend engineers to expose AI capabilities through clean,

well-documented APIs that the builder and runtime consume.

Required Skills & Experience

• 8–10 years in software / ML engineering, with strong recent hands-on experience in LLMs

and agentic systems.

• Hands-on experience with agent-builder / Agent OS platforms — systems where users

build, deploy, and run AI agents — whether through established frameworks or custom-

built orchestration.

• Practical experience with agent frameworks and orchestration approaches (e.g.

LangChain, LlamaIndex, LangGraph, AutoGen, CrewAI, or equivalent custom systems).

• Expert-level Python and fluency across the modern ML / LLM stack.

• Strong understanding of RAG, vector databases (Pinecone, Weaviate, pgvector, Qdrant,

or similar), and embedding models.

• Experience with model serving, inference optimization, and LLMOps.

• Solid grasp of prompt engineering, agent evaluation, and safety / guardrails.

• Working knowledge of AI Gateway concepts (model routing, rate-limiting, caching, multi-

provider management), AI Governance (versioning, audit, usage policies, responsible AI),

and AI Security (prompt-injection defense, data privacy, secure tool execution).

• Familiarity with cloud platforms (AWS / Azure / GCP) and containerized deployment.

Nice to Have

• Experience fine-tuning or deploying open-weight models.

• Contributions to open-source agentic / LLM projects.

• Experience with streaming, function-calling, and tool-use protocols.