ML Engineer (2-5 Years, 50L)

profound.me; Bengaluru; On-site; INR 1,800,000 - 3,200,000; Full time

Job summary

Consumer tech partner company seeks an ML Engineer to own the matchmaking and personalization systems at the heart of the product. You will build the core matching engine, develop ranking and personalization algorithms, and create user embeddings, similarity models, and graph-based matching systems, deploying them to production.

You'll collaborate with Product, Data and Backend teams to ship end-to-end experiences, tackle cold-start and sparse-data problems, and design offline and online

Qualifications

• Built recommendation or personalization systems in a live product.
• Experience with feed ranking, search ranking, discovery, matching, or recommendations.
• Translate ambiguous product questions into clearly defined ML problems.
• Work with noisy, sparse, or incomplete behavioral data.
• Take ML models from experimentation into production.
• Understand recommendation evaluation, experimentation, and A/B testing.
• Familiar with two-tower retrieval.
• Familiar with learning-to-rank.
• Familiar with embeddings and ANN search.
• Familiar with graph-based recommendations.
• Familiar with LLM-based personalization.

Responsibilities

• Build and iterate on the core matchmaking recommendation engine.
• Develop ranking and personalization algorithms for curated feeds.
• Build user embeddings, similarity models, and graph-based matching systems.
• Solve cold-start and sparse-data problems.
• Work with behavioral data to identify signals.
• Design offline and online evaluation frameworks for recommendation quality.
• Deploy models into production with monitoring and observability.
• Collaborate with Product, Data, and Backend teams to ship end-to-end experiences.
• Identify new ML opportunities beyond predefined tasks.

Skills

Recommendation systems

Personalization

Feed ranking

Search ranking

Discovery

Matching

Embeddings

ANN search

Graph-based recs

Two-tower retrieval

LLM personalization

Similarity models

Production ML

Job description

This role is for one of our partner companies, Consumer tech, seed raised $10M

About the role:

We are looking for an ML Engineer to build and own the recommendation and personalization systems at the heart of the product.

You will work on the matchmaking engine, ranking algorithms, user embeddings, similarity models, and cold-start problems that determine who gets shown to whom.

This is a hands‑on IC role for someone who enjoys taking ambiguous consumer‑product problems, translating them into ML problems, finding signal in noisy behavioral data, and shipping systems into production.

You will work closely with the Principal ML Engineer and partner with Product, Data, and Backend teams.

What you'll own:

• Build and iterate on the core matchmaking recommendation engine
• Develop ranking and personalization algorithms for individually curated feeds
• Build user embeddings, similarity models, and graph‑based matching systems
• Solve cold‑start and sparse‑data problems
• Work with behavioral and community interaction data to identify useful recommendation signals
• Design offline and online evaluation frameworks for recommendation quality
• Deploy models into production and improve iteration, monitoring, and observability
• Partner closely with Product, Data, and Backend teams to ship end‑to‑end experiences
• Identify new ML opportunities rather than simply execute predefined tasks

You'll be a great fit if:

• You have built recommendation or personalization systems in a live product
• You have worked on feed ranking, search ranking, discovery, matching, or recommendations
• You can translate ambiguous product questions into clearly defined ML problems
• You are comfortable working with noisy, sparse, or incomplete behavioral data
• You have taken ML models from experimentation into production
• You understand recommendation evaluation, experimentation, and A/B testing
• You have experience with one or more of:
• Two-tower retrieval
• Learning-to-rank
• Embeddings and ANN search
• Similarity models
• Graph-based recommendations
• LLM-based personalization

Experience with consumer products such as social, e-commerce, video, marketplaces, dating, jobs, or content discovery is particularly relevant.