About Fegmo
Fegmo is building an agentic commerce platform that keeps product and marketing content continuously channel-ready across every endpoint, marketplaces, retailer sites, and emerging AI agents. We help retailers, brands, and marketplaces automate ingestion, enrichment, validation, and syndication so teams launch faster, reduce manual work, and improve conversion.
Our platform runs on modern cloud and AI infrastructure (LLMs, retrieval, microservices) and powers workflows such as onboarding, taxonomy and attributes, media generation (images and video), localization, and compliance at enterprise scale.
We are expanding our engineering leadership team in India and building a strong, co-located execution culture in Noida.
Role Overview
We are seeking a hands-on AI Engineering Lead who will own the design and delivery of Fegmo’s AI systems across product content workflows. This is a technical leadership role with high ownership. You will build and ship production AI features, define quality and evaluation standards, and mentor AI engineers while partnering closely with product and platform engineering.
You will be based on-site in Noida with the team and will help grow a small, co-located AI engineering function over time.
In the next 90 days, your primary mission is to stabilize and productionize our AI workflows by improving quality, evaluation rigor, reliability, latency, and cost controls, while maintaining a consistent release cadence.
Key Responsibilities
AI System Ownership and Delivery
- Own end-to-end delivery of AI-powered workflows for product understanding, attribute enrichment, taxonomy, tagging, and validation.
- Build and ship production-grade LLM and retrieval pipelines (RAG, extraction, classification, generation) integrated into core product workflows.
- Define clear service boundaries and interfaces between AI services and the core platform.
Agentic Workflows and Orchestration
- Design and implement agentic workflows for multi-step tasks, planning, and tool use, with strong guardrails and measurable quality.
- Use orchestration frameworks and patterns (tools, function calling, workflows, multi-step pipelines), selecting the simplest approach that meets reliability and cost goals.
Evaluation, Quality, and Reliability
- Own AI evaluation strategy: datasets, metrics, thresholds, regression testing, and release gates for AI changes.
- Implement monitoring for output quality, hallucination risk, latency, and cost, and drive continuous improvement through feedback loops.
- Establish prompt and pipeline versioning, rollout, and rollback practices.
Data and Retrieval Foundations
- Work with embeddings, vector stores, and metadata pipelines for high-precision retrieval and grounding.
- Define data quality requirements for training and evaluation sets, and collaborate on lightweight data curation and labeling processes as needed.
Technical Leadership and Mentorship
- Set engineering standards for AI code quality, documentation, and testing discipline.
- Mentor AI engineers and help the broader engineering team adopt AI patterns safely and consistently.
- Collaborate tightly with US-based leadership, product, and platform teams to align priorities and execution.
Required Skills and Experience
Technical Skills
- 7–12 years of experience in software engineering, ML engineering, or applied AI, with 2+ years shipping GenAI or LLM-powered features to production.
- Strong Python engineering skills, building services and pipelines (FastAPI or similar).
- Hands-on experience with:
- LLM integration, prompt engineering, and structured outputs
- Retrieval pipelines (embeddings, vector search, reranking, grounding)
- Evaluation and monitoring of AI systems in production
- Solid software engineering fundamentals: APIs, background jobs, testing, debugging, and performance.
- Experience with cloud deployment patterns and production operations (CI/CD, Docker, observability).
- Familiarity with modern AI stacks and tooling (framework choice is flexible, LangChain-style tooling is fine but not required).
Leadership Skills
- Ability to lead technical execution end-to-end, with high ownership and strong delivery discipline.
- Comfortable mentoring engineers and raising the quality bar through standards and reviews.
- Strong communication and ability to work with product and engineering stakeholders.
Nice-to-Have
- Experience building agentic workflows, tool-use patterns, or multi-step reasoning pipelines.
- Experience with commerce or catalog systems (PIM/DAM), syndication, marketplaces, or content pipelines.
- Experience with GCP (Cloud Run, VMs, storage, IAM) and production monitoring practices.
- Familiarity with multimodal AI for images and video, and associated media pipelines.
Why Join Fegmo?
- Build foundational AI systems in an early-stage AI-native company.
- Own the AI quality bar and productionization standards for a platform built for enterprise workflows.
- Your contributions will directly shape the product and customer outcomes.
- High ownership and impact, with the opportunity to take on expanded scope as the team grows.
Culture Note
We are building a thoughtful, mission-driven team that values collaboration, creativity, and inclusion. We welcome applicants from all backgrounds and are especially excited to hear from candidates with unique perspectives and a passion for building meaningful tools.
…