GenAI Engineer
Job description
About the role
The role involves building production-ready AI features for business planning workflows. Success in this role requires deep ML knowledge combined with strong software engineering skills.
Software engineers turn product ideas into working code. Engineers work in small teams, review each other's work, and ship in small batches. Most teams follow agile practices such as sprints and daily standups. Engineers also write tests, fix bugs, and improve performance. The field values clear communication as much as technical skill. Engineers spend part of every week on planning, code review, and debugging, not just writing new code. The ability to explain a technical decision in plain words separates strong engineers from the rest.
Key facts
What you'll do
Backend API services, model integration, monitoring, evaluations, and deployments are developed to enable GenAI features for planning workflows.
APIs exposing AI capabilities are designed and developed for Anaplan's platform and third-party integrations.
ML models and forecasting algorithms are productionized in collaboration with data scientists.
Technical design discussions, code reviews, and knowledge-sharing sessions are participated in to align implementation with architecture.
Requirements
5+ years of software engineering experience is required, with 2+ years focused on ML/AI systems.
Python programming skills are required, including experience with ML frameworks such as PyTorch, TensorFlow, and Transformers.
Production deployment of LLM-powered applications is required, with demonstrated experience in building and releasing such systems.
Front-end development proficiency with React, TypeScript, and modern web technologies is required.
Understanding of RESTful API design, microservices architecture, and cloud infrastructure is required.
Experience with prompt engineering and RAG systems is required.
A strong foundation in ML fundamentals, including NLP, time-series analysis, or recommender systems, is required.
Containerization using Docker, orchestration with Kubernetes, and CI/CD pipelines are required.
Excellent problem-solving skills and attention to detail are required.
A Bachelor's degree in computer science, Machine Learning, or a related field is required.
Nice to have
Hands-on experience with GenAI frameworks such as LangChain, LlamaIndex, or Haystack is beneficial.
Knowledge of vector databases like Pinecone, Weaviate, or Qdrant and embedding models is beneficial.
Experience with model serving frameworks including vLLM, TensorRT, or Ray is beneficial.
A background in forecasting, planning, or analytics applications is beneficial.
Prior familiarity with Anaplan or similar enterprise planning platforms is beneficial.
Experience with A/B testing and experimentation frameworks for AI features is beneficial.
Contributions to open-source ML projects or research publications are beneficial.
Experience with model observability tools such as LangSmith, W&B, or MLflow is beneficial.
Skills & tools
The role involves GenAI technologies, LLMs, prompt engineering, RAG, conversational and agentic AI, and production ML systems. Modern front-end frameworks, API design, and cloud infrastructure are used in daily work.
Practical notes
This role is based in Gurugram, India. The position is full-time and requires on-site presence as defined by company policy.
Typical interview steps
Hiring for engineering roles usually starts with a recruiter screen, followed by one or two technical rounds. Candidates often solve a coding problem, discuss past projects, and answer system design questions. Some loops include a take-home task. Final rounds typically cover team fit and give candidates a chance to ask questions. Interviewers look for how you break down an unfamiliar problem, not just whether you reach the answer. Practicing a few problems aloud and reviewing your own past projects are the best preparation.
Good to know
GenAI Engineers design and build AI features that integrate into software products.
The role relies on strong Python skills, familiarity with ML frameworks, and production deployment experience.
Front-end proficiency enables building user-facing AI interfaces with modern web technologies.
Model observability and evaluation frameworks help measure and improve AI quality in production.
Collaboration with data scientists ensures that ML models are production-ready.