AI/ML ENGINEER

Tech Stack

Core Language (Must-Have)

● Python (expert level) – primary language for agentic workflows, GenAI systems, and

data pipelines

● Good to have exposure on Java (for backend integration), REST / GraphQL

GenAI & Agentic Systems (Must-Have)

● LLMs: OpenAI GPT-4+, Claude, Gemini, SLMs

● Agent frameworks: LangChain, LangGraph, MCP, CrewAI

● Agent orchestration, tool-calling, multi-step workflows

Data & RAG Platforms (Must-Have)

● Databricks, Spark / PySpark, Delta Lake

● RAG pipelines, embeddings, vector search

● Vector DBs: FAISS, Pinecone, Weaviate, Chroma (or similar)

Cloud & Production

● AWS (S3, ECS/EKS, Lambda, messaging services)

● APIs (REST / GraphQL), distributed systems

● Docker, Kubernetes, CI/CD

Monitoring & MLOps (Good to Have)

● MLflow, Databricks Jobs / Workflows

● Observability: CloudWatch, Grafana, Prometheus

Role : Senior AI Engineer (GenAI, Agentic Systems & Data Platforms)

Location: Remote (Work from Home)

We are hiring a Senior AI Engineer with deep Python expertise and hands-on

experience building and optimizing agentic workflows in production.

This role is ideal for someone who has evolved from a strong Data Science or

Backend (SDE) foundation into agent-based GenAI systems, and enjoys owning

systems end-to-end — from design to scale, performance, and reliability.

You will work at the intersection of:

● LLMs & Agentic AI

● Databricks / Spark-based data platforms

● Cloud-native backend systems on AWS

Key Responsibilities

Agentic Systems & GenAI

● Design, build, and optimize agentic workflows using LangGraph, LangChain,

MCP, CrewAI, or similar frameworks.

● Build multi-step, tool-calling AI agents that automate real enterprise workflows

(CRS onboarding, sales ops, business rules, analytics).

● Own agent orchestration, state management, retries, fallbacks, and error

handling in production systems.

● Continuously improve agent performance across latency, cost, accuracy, and

determinism.

Data & RAG Platforms

● Build RAG pipelines on Databricks, leveraging Spark/PySpark for:

○ Large-scale document ingestion (PDFs, specs, contracts)

○ Chunking, embeddings, indexing, and retrieval

● Integrate structured (tables, metrics, logs) and unstructured data into agent-driven

systems.

Production Engineering

● Build and deploy LLM-powered APIs and services using Python on AWS.

● Collaborate with Backend and Data Platform teams to productionize workflows using

Databricks Jobs, MLflow, CI/CD, and cloud services.

● Implement guardrails, monitoring, observability, and evaluation for agent behavior in

production.

● Ensure systems meet enterprise-grade reliability, scalability, and cost efficiency

standards.

Mandatory Requirements

Experience

● 5–8 years of overall experience in Data Science, Machine Learning, or Backend

(SDE) roles.

● Minimum 2 years of hands-on experience building agentic or workflow-driven AI

systems in production.

Core Skills (Non-Negotiable)

● Expert-level Python — this is mandatory and core to the role.

● Proven experience designing and shipping production GenAI systems, not just

prototypes.

● Strong hands-on experience with Databricks, Spark / PySpark, and data

pipelines.

● Practical experience with LLMs, RAG pipelines, embeddings, and vector search.

● Experience working with AWS-native architectures (S3, ECS/EKS/Lambda,

messaging systems).

● Solid engineering fundamentals: APIs, distributed systems, CI/CD,

Docker/Kubernetes.

Nice to Have

● Experience with Databricks Vector Search, MLflow, Feature Store.

● Understanding of LLM internals, prompt optimization, inference tuning, and SLM

strategies.

● Experience building cost-efficient, low-latency AI systems at scale.

● Familiarity with enterprise workflow automation (sales ops, support, analytics).

● Domain exposure to travel-tech, marketplaces, pricing/availability systems.

Why Join Us?

● Work on real production agentic systems at massive scale — not demos or

POCs.

● Direct impact on GMV growth, revenue yield, and operational automation.

● Ownership of core AI infrastructure in a fast-growing, VC-backed company.

● Strong engineering culture with deep focus on performance, cost, and

reliability.

● Opportunity to help define the agent-driven foundation of a global B2B

platform.