Full-Time
AI Engineer
Virallens
No salary listed
Bengaluru, Karnataka, India
In Person
Master's, PhD
Category
 Software Engineering (1) |
|---|
Required Skills
Kubernetes
Pinecone
Microsoft Azure
Python
Distributed Systems
React.js
TensorFlow
PyTorch
Machine Learning
OpenAI
ETL
Docker
RAG
AWS
Next.js
Observability
LangChain
Data Governance
Google Cloud Platform
Requirements
- 3–8 years of software engineering experience with deep expertise in Python.
- Experience building and deploying retrieval-augmented generation or information-retrieval systems.
- Strong proficiency in TensorFlow and PyTorch.
- Ability to design hybrid retrieval pipelines, encode knowledge using large language models and vector stores, and build and optimize retrieval-augmented generation systems.
- Proficiency with vector databases and search libraries such as pgvector, FAISS, Milvus, Pinecone, or Weaviate.
- Strong understanding of vector search algorithms, indexing strategies, and hybrid search techniques.
- Hands-on experience with embeddings and transformer-based models such as OpenAI, Cohere, or Sentence Transformers, and frameworks such as Hugging Face Transformers, LangChain, and LlamaIndex.
- Practical knowledge of distributed systems, extract, transform, and load pipelines, Docker, Kubernetes, and cloud platforms such as Azure, Amazon Web Services, or Google Cloud Platform for deploying AI applications.
- Familiarity with evaluation of retrieval systems, observability tools, and model performance monitoring.
- Understanding of data governance, security, and compliance considerations.
Responsibilities
- Design, prototype, and deploy retrieval-augmented generation systems by architecting scalable retrieval-augmented generation pipelines that combine vector search, hybrid retrieval, re-ranking, and contextual compression techniques.
- Build and integrate vector search systems such as Milvus, pgvector, FAISS, or Weaviate for high-recall retrieval across structured and unstructured data.
- Design hybrid retrieval systems that blend semantic, symbolic, and graph-based methods.
- Create custom chunking and encoding strategies to store operational knowledge in vector databases and knowledge graphs.
- Architect knowledge graphs using Neo4j, Resource Description Framework, or custom schemas, and integrate them into retrieval workflows to support reasoning and decision-making.
- Build and optimize data pipelines that convert incoming documents into high-quality embeddings for AI retrieval.
- Tune chunk sizes, indexing frequencies, and embedding strategies to enhance recall, factual accuracy, and efficiency.
- Combine semantic and keyword search to improve precision and efficiency, and experiment with metadata filtering techniques to surface relevant context for AI reasoning agents.
- Evaluate end-to-end retrieval performance using classical information-retrieval metrics such as precision and recall and large-language-model-specific evaluations such as factuality, coherence, and task success.
- Monitor retrieval logs and adjust embedding configurations to maintain relevance and mitigate hallucinations.
- Compare the performance of different large language models such as GPT-4, Claude, and Llama across embedding structures and refine tuning strategies.
- Implement quantization, distillation, and optimization techniques to meet latency, throughput, and cost targets.
- Work cross-functionally with product managers, data engineers, and domain experts to translate product goals into scalable AI solutions.
- Conduct workshops and enablement sessions to enhance AI literacy across internal teams.
- Participate in rigorous code reviews and implement testing frameworks to ensure reliability, security, and compliance.
- Continuously monitor model accuracy and safety and uphold data governance and ethical guidelines.
Desired Qualifications
- Experience designing and deploying knowledge graphs, semantic graphs, or multimodal search systems.
- Familiarity with large-language-model fine-tuning, reinforcement learning from human feedback, and safety alignment.
- Exposure to multimodal models for image, video, or audio and diffusion models.
- Contributions to open-source generative artificial intelligence, retrieval, or vector database projects, or published research or blogs.
- Experience with React or Next.js for rapid prototyping of AI-driven applications.
- A preferred Master's or PhD in Computer Science, Artificial Intelligence, Machine Learning, or a related field; extensive relevant experience or significant open-source contributions may substitute for formal education.