๐ง๐ต๐ถ๐ ๐ฟ๐ผ๐น๐ฒ ๐ถ๐ ๐ณ๐ผ๐ฟ ๐ผ๐ป๐ฒ ๐ผ๐ณ ๐๐ต๐ฒ ๐ช๐ฒ๐ฒ๐ธ๐ฑ๐ฎ๐'๐ ๐ฐ๐น๐ถ๐ฒ๐ป๐๐
๐ฆ๐ฎ๐น๐ฎ๐ฟ๐ ๐ฟ๐ฎ๐ป๐ด๐ฒ: ๐ฅ๐ ๐ฏ๐ด๐ฌ๐ฌ๐ฌ๐ฌ๐ฌ - ๐ฅ๐ ๐ฑ๐ฑ๐ฌ๐ฌ๐ฌ๐ฌ๐ฌ (๐ถ๐ฒ ๐๐ก๐ฅ ๐ฏ๐ด-๐ฑ๐ฑ ๐๐ฃ๐)
Experience: 4+ yrs
Location: Bangalore
We are looking for a highly skilledย Senior Applied AI Engineerย to build and scale production-grade AI systems that enable intelligent, reliable, and personalized healthcare experiences. This role combinesย applied AI, LLM engineering, backend development, agentic workflows, clinical reasoning, and AI safetyย to deliver technology that improves healthcare accessibility and user outcomes.
The ideal candidate will have strong Python and backend engineering expertise, hands-on experience deploying AI systems in production, and the ability to solve complex problems in high-stakes environments. You will help transform advanced AI capabilities into dependable healthcare products with measurable performance, safety, and reliability.
Requirements
Key Responsibilities
- Design and deploy AI-powered clinical workflows that reason across patient history, symptoms, medications, lab reports, and relevant medical information.
- Build agentic AI architectures and multi-agent systems for clinical reasoning, information retrieval, verification, risk assessment, and escalation.
- Develop backend services, APIs, data pipelines, and model orchestration systems usingย Pythonย and modern engineering frameworks.
- Build scalable RAG pipelines that retrieve relevant information from trusted medical sources, clinical guidelines, prescriptions, and patient health records.
- Implement prompt engineering, context management, model routing, verifier layers, and uncertainty detection to improve response quality.
- Develop comprehensive AI evaluation frameworks, including simulated-patient testing, regression benchmarks, red-team scenarios, and clinical safety metrics.
- Measure and improve clinical accuracy, hallucination risk, escalation quality, empathy, response relevance, and overall system reliability.
- Implement safety mechanisms for high-risk situations, including emergency escalation, human review, uncertainty handling, and fail-safe behaviour.
- Build AI features for web, mobile, messaging, and other digital healthcare experiences.
- Improve the processing of unstructured and complex inputs, including PDFs, laboratory reports, prescriptions, incomplete medical histories, and longitudinal patient context.
- Optimise AI systems for latency, scalability, cost efficiency, monitoring, and production stability.
- Diagnose and resolve issues across application, model, data, and infrastructure layers.
- Collaborate with clinicians, medical reviewers, product teams, and engineers to translate clinical judgement into reliable software.
- Establish best practices for AI testing, privacy, observability, auditability, and continuous deployment.
What Makes You a Great Fit
- 4+ years of relevant experience, with strong hands-on expertise in production software engineering and applied AI.
- Strong proficiency inย Pythonย and backend application development.
- Proven experience building and deploying production-grade LLM, machine learning, or data-intensive systems beyond experimental prototypes.
- Strong understanding of APIs, distributed systems, testing, monitoring, and production reliability.
- Practical experience with RAG, prompt and context engineering, AI agents, model routing, fine-tuning, evaluation, or model deployment.
- Familiarity with frameworks and technologies such asย FastAPI, PyTorch, TensorFlow, LangGraph, LangChain, LlamaIndex, vector databases, and LLM observability tools.
- Strong analytical and problem-solving skills, with the ability to navigate ambiguous technical challenges.
- High product ownership and sound judgement when balancing accuracy, user experience, safety, performance, and cost.
- Ability to collaborate effectively with engineering, product, and clinical stakeholders.
- Excellent written and verbal communication skills, including the ability to explain complex technical trade-offs clearly.
- A strong commitment to responsible AI, privacy, clinical safety, and measurable production quality.