JOB DESCRIPTION
HOMESLY Company: Homesly Position: AI Engineer Department: Engineering / Technology 1. Role Overview Homesly is looking for an AI Engineer to design, develop, deploy, and maintain reliable AI-powered applications that solve real business problems. The role combines Python backend development, Machine Learning, Generative AI, LLMs, Retrieval-Augmented Generation (RAG), and agentic workflows. The successful candidate will build practical solutions, integrate AI with business systems, and help ensure production applications are secure, scalable, reliable, and cost-effective. **2.

Key Responsibilities
AI, LLM & Automation*
*
- Build and maintain AI
- and LLM-powered applications using OpenAI, Anthropic, Gemini, and other model providers.
- Develop RAG pipelines covering document ingestion, chunking, embeddings, hybrid search, reranking, and retrieval evaluation.
- Create agentic workflows using tool/function calling, LangGraph, MCP, structured outputs, and appropriate human review.
- Apply prompt engineering, model evaluation, fine-tuning where appropriate, and guardrails to improve quality and safety.
- Measure accuracy, relevance, hallucinations, latency, and cost; maintain evaluation and regression test sets. Backend, Data & Integrations
- Develop backend services and APIs using Python and FastAPI, Django, or Flask.
- Connect AI systems to business platforms and workflows such as booking, pricing, email, and WhatsApp.
- Integrate third-party services using REST APIs, webhooks, asynchronous tasks, and queues.
- Build data ingestion, preprocessing, indexing, and background-job pipelines with safe retries and failure handling.
- Design and maintain database schemas and work with PostgreSQL, pgvector, Redis, vector databases, and search platforms. Deployment, Reliability & Collaboration
- Deploy and operate services on AWS, GCP, or Azure using Docker and CI/CD; work with Kubernetes and Terraform where needed.
- Implement logging, tracing, metrics, monitoring, alerts, rollback, access controls, and secrets management.
- Debug issues to root cause, add tests to prevent recurrence, and document runbooks and technical decisions.
- Collaborate with product, engineering, and business stakeholders; participate in code reviews and share technical knowledge. **3. Required Technical Skills Programming & Backend*
*
- Python; advanced SQL; Bash and Linux; Git/GitHub. TypeScript/Node.js or Go is an advantage.
- FastAPI,



Django, or Flask; REST APIs, gRPC, webhooks, asynchronous programming, and background queues such as Celery, SQS, or Kafka. Data, ML & Generative AI
- PostgreSQL, pgvector, Redis, FAISS/Pinecone or similar vector databases, Elasticsearch/OpenSearch, Pandas, and NumPy.
- PyTorch, scikit-learn, Hugging Face Transformers, embeddings, model evaluation, and fine-tuning concepts such as LoRA.
- LLM APIs, prompt engineering, RAG, hybrid search, reranking, agents, LangGraph, LlamaIndex, MCP, structured outputs, and guardrails. Cloud, DevOps & Quality
- AWS, GCP, or Azure; Docker; CI/CD (for example, GitHub Actions); familiarity with Kubernetes, Terraform, IAM, and secrets management.
- Pytest, automated/API testing, mocked integrations, logging, tracing, metrics, and LLM monitoring tools such as Langfuse. 4. Engineering & System Design Expectations
- Design maintainable services and multi-component architectures with appropriate isolation, scaling, and service communication.
- Build for production reliability using retries, idempotency, rate limits, timeouts, secure deployments, and rollback strategies.
- Manage latency and cost through caching, sensible model routing, token budgets, and efficient database queries.
- Use evaluation data, regression checks, and faithfulness/accuracy measures to assess AI quality over time.
- Recognize data quality issues, schema requirements, drift, and the need for appropriate labeling.
- Protect systems and users through privacy controls, PII handling, access management, and prompt-injection defenses.
- Choose solutions pragmatically: know when an LLM is useful and when conventional software is simpler and safer. 5. Hands-on Development Expectations
- Write clean, modular, readable, tested codenot notebook-only prototypes.
- Build and deploy an end-to-end service involving an API, database, Docker, and cloud hosting.
- Use Git daily, including branches, pull requests, rebasing, conflict resolution, and code review.
- Write Pytest tests, mock external APIs, investigate production logs,



trace failures, and fix root causes.
- Use SQL and Bash for audits, migrations, operational tasks, and automation.
- Build a small frontend or dashboard with React/Next.js when the project requires it.
- Document APIs, architecture, deployment steps, and operational procedures. 6. General AI Engineering Responsibilities
- Translate business needs into useful AI solutions and select the simplest approach that meets the requirement.
- Prepare and clean data, create data pipelines, and select, prompt, fine-tune, or train models as appropriate.
- Deploy models and AI features as reliable services and monitor performance, drift, cost, and failures after launch.
- Apply safety, privacy, and responsible-AI practices throughout development and operation.
- Work with product, developers, and stakeholders to deliver measurable business outcomes. 7. Collaboration & Ownership
- Take responsibility for assigned features and services from design through deployment and ongoing improvement.
- Explain technical choices and trade-offs to technical and non-technical colleagues.
- Estimate work, communicate progress and risks, contribute to design discussions, and support code quality.
- Share knowledge and collaborate with other engineers to improve team practices. 8. Preferred Qualifications
- Degree or equivalent practical experience in Computer Science, AI, Machine Learning, or a related field.
- Practical experience building and deploying software, AI/ML, or Generative AI applications.
- Experience connecting LLMs to real-world business workflows and integrating third-party services.
- Experience with cloud infrastructure, production monitoring, testing, and application security.
- Strong analytical thinking, communication, debugging, and problem-solving skills. 9. What Success Looks Like- Deliver useful, reliable AI features that support real Homesly business workflows.
- Improve response quality and automation while controlling latency and operating costs.
- Maintain services that are observable, testable, secure, and straightforward to operate.
- Identify and resolve issues systematically and continuously improve system quality. The AI Engineer is expected to do more than connect an application to a model: understand the problem, design a suitable solution, write production-quality code, test it, deploy it, monitor it, and improve it.

📌 Artificial Intelligence Engineer (Hyderabad)
🏢 Homesly Properties
📍 Hyderabad