Lead-ML Engineer

Ovii's Interpretation of the Role

We’re seeking a Lead ML Engineer to own and scale a next‑generation hybrid search platform, bridging advanced information‑retrieval models with high‑throughput production systems. You’ll design, build, and evaluate vector‑plus‑lexical pipelines, ensure sub‑second latency, mentor engineers, and collaborate closely with product and data stakeholders.

Role Snapshot

• Lead ML Engineer
• Hybrid search platform ownership
• Vector & lexical search architecture
• Performance & latency optimization
• ML model integration & evaluation
• Mentorship & team leadership
• Cross‑functional collaboration

Must-Have Requirements

• Vector databases (Pinecone, Milvus, Qdrant)
• Search engines (Elasticsearch, OpenSearch)
• Reranking models (BGE, Cohere)
• Fusion techniques (Reciprocal Rank Fusion)
• Load testing tools (Locust, k6)
• Google Cloud Firestore
• MLOps pipelines (Kubeflow, Airflow, Dagster)
• Statistical evaluation for search quality (NDCG, MRR, Recall)
• Google Cloud Professional Machine Learning Engineer certification
• TensorFlow Developer certification
• Machine Learning engineering
• Search relevance
• MLOps
• B.Tech or B.E. in Computer Science, Information Technology, or related field
• Google Cloud Professional Machine Learning Engineer
• TensorFlow Developer

Nice-to-Have Signals

• Computer vision
• Recommender systems
• Knowledge graph construction
• Entity resolution pipelines
• E‑commerce or supply‑chain search experience
• Model serving and monitoring frameworks (Vertex AI, Azure ML)
• Computer Vision
• Recommender Systems
• Knowledge graph
• Master’s degree in Machine Learning, Data Science, or Artificial Intelligence
• E‑commerce
• Supply Chain

Work Setup

• Location: Hyderabad, India
• Work mode: HYBRID
• Employment type: Full-Time

Eligibility Gates

• Visa sponsorship: unknown

Not Specified in JD

• Visa sponsorship
• Salary range
• Remote eligibility
• Notice period
• Travel requirements

What You'll Likely Work On

• Design and implement a hybrid search engine that combines vector (semantic) and lexical (BM25) retrieval, integrating reranking models and blending strategies.
• Build and maintain automated evaluation harnesses and quality benchmarks to monitor relevance metrics such as NDCG, MRR, and Recall.
• Conduct systematic load testing and optimize infrastructure to meet a strict SLA of sub‑500 ms P95 latency at peak load.
• Manage master data ingestion pipelines and govern schema/configuration in Google Cloud Firestore, collaborating with data‑governance teams.
• Partner with DevOps/MLOps to develop scalable deployment patterns for search and ranking models using CI/CD and orchestration tools.
• Mentor junior and mid‑level engineers through code reviews and technical guidance.
• Lead cross‑functional AI/ML project teams and communicate technical decisions to both technical peers and non‑technical stakeholders.

Good Fit If You Have

• Experience with e‑commerce or supply‑chain search domains (nice to have).
• Background in computer vision or recommender systems (advantageous).
• Familiarity with knowledge‑graph construction or entity‑resolution pipelines (optional).