19 Nov
|
Latentview
|
Bengaluru
19 Nov
Latentview
Bengaluru
Job Summary
We are seeking a highly skilled AI Engineer Production AI Agents to collaborate with Product, Research, Engineering, and business teams to design, develop, and scale production-grade AI-powered applications and intelligent agent systems.
The ideal candidate will have strong expertise in Generative AI, LLM-based agents, multi-agent orchestration, and Retrieval-Augmented Generation (RAG), along with a solid foundation in backend and full-stack engineering. The candidate should be passionate about taking AI solutions beyond experimentation and delivering robust, high-performance systems that integrate seamlessly into real-world applications.
Key Responsibilities
- Design, develop, and scale stateful, multi-agent AI systems using modern orchestration frameworks to enable reliable and scalable workflows for insights generation and synthesis.
- Collaborate with Product, Research, Engineering, and business stakeholders to translate business requirements into end-to-end AI solutions, from proof of concept to evaluation and production deployment.
- Design and implement advanced Retrieval-Augmented Generation (RAG) pipelines, incorporating hybrid search, re-ranking, vector search, and other advanced retrieval techniques.
- Build evaluation frameworks and pipelines, including LLM-as-a-Judge and automated benchmarks, to measure system performance, accuracy, reliability, and response quality.
- Develop and maintain scalable backend services for high-throughput, low-latency AI workloads, while contributing to lightweight frontend components and internal tools.
- Optimize batching, streaming, caching, and request orchestration in distributed and asynchronous environments to improve application performance and efficiency.
- Continuously improve production AI systems across latency, throughput, reliability, observability, and infrastructure costs.
- Collaborate with infrastructure teams to leverage GPU-enabled environments and cloud-native technologies for efficient AI deployment and inference.
- Establish monitoring, tracing, and observability practices for complex AI systems to ensure performance, reliability, and production readiness.
- Develop reusable platform components, Model Context Protocols (MCPs), APIs, SDKs, and best practices for AI application development.
- Evaluate and adopt emerging AI technologies, including reasoning models, Small Language Models (SLMs),
and advanced prompting strategies, based on business impact and system reliability.
- Partner with cross-functional teams to ensure AI solutions adhere to responsible AI, data privacy, and security standards.
Qualifications & Experience
- Bachelor's or Master's degree in Computer Science, Engineering, Artificial Intelligence, Data Science, or a related technical discipline (or equivalent practical experience).
- 7+ years of professional experience in software engineering, AI/ML engineering, or full-stack development, with hands-on ownership of production-grade applications and platforms.
- 4+ years of focused experience building and deploying AI-centric systems.
- 2+ years of hands-on experience developing LLM-based agents, autonomous workflows, or multi-agent orchestration systems.
- Strong full-stack engineering experience with deep expertise in Python and familiarity with TypeScript or Node.js.
- Hands-on experience with AI orchestration frameworks such as LangGraph, LlamaIndex Workflows, or similar technologies.
- Strong understanding of Retrieval-Augmented Generation (RAG), including hybrid search, re-ranking, vector retrieval, and advanced retrieval strategies.
- Experience implementing AI observability, monitoring, and tracing solutions using tools such as LangSmith, Langfuse, or Arize Phoenix.
- Production experience with modern machine learning frameworks and tools such as PyTorch, Transformers, and scikit-learn.
- Proven experience taking AI-powered products from prototype to production, ensuring scalability, maintainability, and operational excellence.
- Experience designing and implementing evaluation pipelines, automated testing frameworks, and quality benchmarks to improve AI reliability and reduce hallucinations.
- Hands-on experience working with APIs and SDKs from major model providers, including OpenAI, Anthropic, and Gemini, as well as open-source models.
- Experience deploying and managing applications on cloud platforms such as AWS, Azure, or GCP.
- Strong understanding of containerization and orchestration technologies, including Docker and Kubernetes.
- Familiarity with CI/CD pipelines, DevOps practices, and production deployment workflows.
- Excellent problem-solving, communication, and collaboration skills, with the ability to work effectively across technical and non-technical teams.
Preferred Skills & Domain Expertise
- Experience with Spring-based service development and enterprise application architecture.
- Familiarity with big data processing ecosystems such as Apache Spark and Hadoop.
- Experience with streaming technologies such as Kafka, Flink, or Apache Beam.
- Hands-on experience building advanced RAG pipelines, integrating vector databases, tool-use frameworks, and multimodal AI models.
- Proficiency with vector databases such as Pinecone, Weaviate, Qdrant, or pgvector.
- Exposure to GPU optimization and inference performance tuning techniques, including CUDA and model inference optimization.
- Experience building conversational AI systems involving intents, entities, dialogue flows, and interaction design.
- Familiarity with prompt optimization and programming frameworks such as DSPy.
- Experience with graph databases such as Neo4j and GraphRAG architectures.
- Exposure to voice agents, multimodal AI applications, and conversational interfaces.
- Foundational knowledge of machine learning, model fine-tuning, and model optimization techniques.
- Experience designing reusable AI platforms, agent tools, MCP integrations, and enterprise-grade APIs.
Why Join Us?
- multi-agent systems, RAG, and multimodal AI.
- Opportunity to transform cutting-edge AI research and experimentation into scalable, business-critical production solutions.
- Collaborate with cross-functional teams across Product, Research, Engineering, and business functions.
- A culture that encourages innovation, continuous learning, experimentation, and evaluation-driven development.
- Collaborative, inclusive, and dynamic work environment at the intersection of AI research, product innovation, and software engineering.
We are an equal opportunity employer and value diversity at our company. We do not discriminate on the basis of race, religion, color, national origin, sex, gender, gender expression, sexual orientation, age, marital status, veteran status, or disability status.
📌 LatentView | AI Full Stack Developer | Bangalore (Bengaluru)
🏢 Latentview
📍 Bengaluru