Senior Applied Scientist - Semantics

AuxoAI is seeking a Senior Applied Scientist to design and deploy structured knowledge systems that enable reliable, schema-grounded AI and agent reasoning.

This role sits at the intersection of large language models, knowledge graphs, semantic architectures, and hybrid retrieval systems. The ideal candidate will build systems that transform unstructured data into structured knowledge representations, enforce semantic constraints, and enable hybrid symbolic–neural reasoning in production environments.

You will play a key role in designing scalable semantic infrastructures that support advanced AI use cases such as GraphRAG pipelines, structured extraction, and agent reasoning workflows.

You will work on problems where existing architectures may not be sufficient and will experiment with new approaches that combine machine learning, knowledge graphs, semantic constraints, and classical AI techniques to build reliable, production-grade systems.

Location - Mumbai/Bangalore/Hyderabad/Gurgaon (Hybrid - 3 Days a week in Office)

Responsibilities:

• Design schema-guided information extraction systems using zero-shot and few-shot structured prompting, constrained decoding approaches such as JSON schema enforcement or grammar-based decoding, and function-calling or tool-driven extraction techniques.
• Develop recursive or multi-stage extraction pipelines capable of handling nested entities, hierarchical structures, and cross-document relationships.
• Build ontology-driven systems using frameworks such as LinkML, OWL, SHACL, or similar schema modeling tools, and implement knowledge representations using RDF triples or labeled property graphs.
• Design and optimize entity resolution algorithms using techniques such as blocking strategies, embedding similarity, and rule-based matching.
• Develop ontology alignment techniques and graph embedding models such as Node2Vec or TransE-style approaches where appropriate.
• Design hybrid retrieval architectures combining dense vector retrieval, sparse retrieval techniques, and graph traversal algorithms such as BFS, DFS, path ranking, and neighborhood expansion.
• Build validation systems that enforce schema conformance, detect semantic inconsistencies, and reduce hallucinated or invalid structured outputs.
• Integrate structured knowledge systems into GraphRAG pipelines, agent planning frameworks, and tool-selection workflows.
• Deliver production-grade semantic systems with clear targets for latency, scalability, reliability, and data integrity.

Requirements

• 5+ years of experience building production AI or machine learning systems.
• Strong experience designing and implementing knowledge graphs or ontology-driven architectures.
• Hands-on experience implementing structured extraction techniques, including grammar-constrained decoding, JSON schema enforcement, or AST-style parsing approaches.
• Experience building entity resolution systems beyond simple embedding similarity methods.
• Experience working with graph query languages such as SPARQL or Cypher and optimizing graph query performance.
• Familiarity with RDF, OWL, or property graph data models and semantic data architectures.
• Strong Python engineering skills, with emphasis on data validation, schema integrity, and system reliability.
• Experience designing hybrid symbolic and neural AI systems.

Nice to Have:

• Experience implementing graph algorithms such as PageRank, community detection, or shortest-path algorithms for reasoning chains.
• Experience building graph-enhanced retrieval systems such as GraphRAG.
• Experience designing compositional semantic extraction pipelines.
• Experience implementing reasoning engines or rule-based inference systems.
• Experience benchmarking and evaluating structural extraction accuracy and consistency.

Lead RAG / Knowledge AI Engineer - (Freelance)

Positions: 1

Experience: Ideally 6–10 years, with strong recent production RAG experience.

Mission

Own UC1's permission-aware enterprise knowledge and retrieval architecture.

Mandatory capabilities

• Python
• Production RAG
• Embeddings
• Vector search
• Hybrid search
• BM25/sparse retrieval
• Semantic search
• Document chunking
• Metadata extraction/filtering
• Query transformation
• Reranking
• Context engineering
• Grounded generation
• Citation generation
• Hallucination mitigation
• RAG evaluation

Strong experience with Milvus, pgvector, Qdrant, Weaviate, Pinecone, Elasticsearch/OpenSearch vector search or equivalent.

Major differentiator

Prior implementation of:

User Identity $B"*(J Source ACL $B"*(J Retrieval Filter $B"*(J Search $B"*(J Reranking $B"*(J Authorized Context $B"*(J LLM

Experience with SharePoint, Microsoft Graph, Microsoft 365, Confluence and Entra ID/Azure AD should receive significant preference.

Roles & Responsibilities

• Design and build ontologies (knowledge models) that organize Dell's business information in a structured way.
• Connect data from different systems so that all information is consistent and easy to understand.
• Create relationships between products, customers, services, and other business data to improve search and AI capabilities.
• Work closely with business teams to understand their requirements and convert them into structured knowledge models.
• Ensure data is organized according to industry standards such as RDF, OWL, and SPARQL.
• Improve enterprise search, analytics, and AI-driven applications by maintaining accurate knowledge structures.
• Collaborate with developers, data engineers, AI teams, and business stakeholders on knowledge management projects.
• Manage and update ontologies as new products, services, and business information are introduced.
• Support knowledge graph and metadata initiatives to improve data quality and consistency.
• Use graph databases and ontology management tools (where applicable) to maintain semantic data models.

Ideal Candidate

• Strong Ontologist Profile with deep semantic (RDF) ontology experience in complex enterprise environments
• Mandatory (Experience 1) – Must have 7+ years of total experience, with 5+ years in semantic (RDF) ontology building/structuring for a complex/large enterprises
• Mandatory (Experience 2) – Must have a strong understanding of content and information management, data structures, and semantic metadata extraction
• Mandatory (Tech skill 1) – Must have strong experience with graph databases, taxonomies, and NLP strategies for optimization
• Mandatory (Tech skill 2) – Must have strong working experience of ontology/TOMS tools such as PoolParty (Semantic Web), TopQuadrant EDG, or GraphDB (Ontotext)
• Mandatory (Tech skill 3) – Must be familiar with W3C industry standards, including SPARQL and OWL.
• Mandatory (Communication) – Must be fluent in English, with strong stakeholder management skills to operate across a complex, multi-team environment.many stakeholders.
• Mandatory (Note) – Must be available to work during US time zones for at least 4 hours per day
• Preferred (Education) – Must have a degree in Computer Science or Library Science, preferably with a minor / concentration / certificate in Information Management or Library Automation
• Preferred (Tech skill 3) – Understanding of content development and search/retrieval tools.

AuxoAI is hiring a Senior Applied Scientist to design and deploy production-grade AI agents capable of structured reasoning, planning, and decision-making.

This role focuses on building reasoning and decision systems using planning algorithms, search methods, and optimization techniques, rather than chatbot or RAG-style application development. The ideal candidate will design intelligent agent architectures that combine LLM-based reasoning with classical planning, search algorithms, and optimization techniques, operating reliably in real-world environments with constraints around latency, cost, uncertainty, and limited context windows.

You will work on advanced AI systems that power autonomous workflows, decision engines, and tool-driven agent ecosystems.

You will also work on problems where existing architectures may not be sufficient, and will be expected to experiment with new approaches that combine machine learning, graph algorithms, and classical AI techniques to build reliable, production-grade systems.

Location - Mumbai/Bangalore/Hyderabad/Gurgaon (Hybrid - 3 Days a week in Office)

Responsibilities:

• Design and architect modular AI agent frameworks incorporating skill decomposition, tool orchestration, and persistent state tracking.
• Implement planning and search algorithms such as Monte Carlo Tree Search (MCTS), beam search, A search, heuristic search, and graph-based planning approaches* to support complex decision-making tasks.
• Develop decision-making loops that balance trade-offs between exploration vs. exploitation, cost vs. accuracy, and latency vs. reasoning depth.
• Build structured memory systems including episodic memory stores, semantic memory layers, and vector-based memory with optimized retrieval strategies.
• Design tool-calling architectures with strong execution validation, retry mechanisms, and failure recovery strategies.
• Develop evaluation frameworks to measure agent performance using task success metrics, rollout simulations, and multi-sample validation approaches.
• Improve agent performance through techniques such as distillation, synthetic trajectory generation, prompt compression, and context pruning.
• Deliver production-ready agent systems that meet operational requirements around reliability, cost efficiency, throughput, and observability.

Requirements

• 3-10 years of experience building machine learning or AI systems in production environments.
• Strong experience implementing search or planning algorithms beyond basic use cases, including tree search or heuristic-based planning approaches.
• Hands-on experience with Monte Carlo Tree Search (MCTS) or related decision-making frameworks.
• Strong understanding of state-space representations, heuristic design, and decision boundary trade-offs.
• Experience building or extensively customizing agent frameworks for real-world applications.
• Hands-on experience designing tool-use or function-calling architectures under practical system constraints.
• Strong Python engineering skills with a focus on scalable and reliable system design.
• 
  

Candidates whose primary experience is limited to RAG pipelines, prompt engineering, or chatbot frameworks without deeper algorithmic or systems work may not be a fit for this role.

Nice to Have:

• Experience with reinforcement learning techniques such as policy gradients, value estimation, or reward modeling.
• Experience building multi-agent or collaborative agent systems.
• Experience designing evaluation frameworks for agent robustness and reliability.
• Experience optimizing LLM inference pipelines for latency, throughput, and cost efficiency.
• Familiarity with distributed task orchestration systems and large-scale AI workflow management.

Senior AI Engineer

Code Generation, Agent Architecture & LLM Systems

📍 Mumbai (On-site) | Full-time | 5+ years

About the Role:

Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.

We are hiring a Senior AI Engineer for a dedicated client engagement focused on building an AI-powered application builder platform - a product where users describe software in plain English and the system generates, previews, and iteratively refines working code.

The mandatory requirement for this role is hands-on production experience shipping LLM-powered systems with agent architectures, with experience in code generation or developer tooling contexts a strong advantage.

The role is product-focused and deeply hands-on. You will own everything between the user's prompt and correct code landing in the project: the agentic loop, code generation pipeline, context management, evaluation suite, and model cost strategy.

You will work alongside the Senior MLOps Engineer who operationalises the infrastructure around your system, and collaborate closely with backend, frontend, and DevOps engineers.

Responsibilities:

Agent Architecture

Design and own the agentic loop for the platform - request interpretation, planning, tool-calling sequence (read file, edit file, run build, search code, install package), and stop conditions.

Make and revisit architectural decisions on single-agent vs. multi-agent designs, including planner/executor splits and dedicated build-repair sub-agents.

Code Generation Pipeline

Own the end-to-end generation flow: task classification, context gathering, planning, targeted edits, verification, and commit.

Implement diff/search-replace-based file editing with fuzzy matching and fallback strategies.

Enforce scope discipline so the agent makes minimal diffs and does not modify code it was not asked to touch.

Self-Repair Loop

Build and tune the automated repair loop that pipes compiler, lint, build, and runtime errors back to the model with retry budgets and model escalation.

This loop is the primary quality lever - the difference between 60-70% and 90%+ build success rates.

Context Management

Build file-relevance retrieval so the agent sees the right files, not the whole codebase: dependency graphs, AST/tree-sitter-based chunking, embeddings, recency signals, and hybrid retrieval.

Implement conversation summarisation and memory for long sessions, and address long-project degradation through codebase summaries and periodic consistency passes.

Own token budgeting and prompt caching strategy.

Prompt Engineering as a Discipline

Own the system prompt and per-task prompt variants (new feature, bug fix, styling change).

Maintain few-shot examples and enforce coding conventions, stack rules, and prohibited behaviours such as no hardcoded secrets and no whole-file rewrites.

Version prompts like code with changelogs and rollback capability.

Evaluation and Quality Measurement

Design and own the evaluation suite: representative test prompts run on every prompt and model change, scored on build success rate, instruction adherence, and output quality including LLM-as-judge and visual/screenshot checks where relevant.

Define regression gates that block quality-degrading changes from shipping.

Treat evals the way engineers treat automated testing: versioned, automated, and tracked over time.

This responsibility is non-negotiable at this level.

Model Strategy and Cost

Design model routing - cheap and fast models for classification and small edits, frontier models for complex generation.

Drive cost optimisation through prompt caching, diff-based edits over full-file rewrites, and tighter context selection.

Track cost per agent run and tokens per task; evaluate new model releases against the eval suite and lead migrations when results justify it.

Safety and Reliability of Agent Behaviour

Defend against prompt injection from user content and fetched web content.

Ensure secrets never appear in generated client code.

Define what the agent's tools may and may not do in collaboration with the platform team.

Contribute to output moderation and abuse-pattern awareness.

Mentorship and Engineering Standards

Run code reviews, define engineering conventions for AI work, and raise the engineering bar across the AI team.

Work closely with the Senior MLOps Engineer on handoff of eval design, prompt configurations, and model routing logic.

Requirements:

Hands-on Production Ownership of LLM-Powered Systems with Agent Architectures (Mandatory)

Must have personally shipped and operated at least one complex production AI system - agentic, multi-step, or code generation - with end-to-end ownership of architecture, evaluation, and cost.

POCs, internal demos, and tutorial-grade work do not qualify.

5+ Years of Professional Software or AI Engineering Experience

With at least 3 years focused on LLM applications, AI engineering, or production AI systems.

Candidates with strong backend backgrounds and a clear, substantive pivot into LLM systems qualify.

Strong Python Proficiency and Service Development

Production-grade Python with FastAPI or equivalent: type hints, async patterns, streaming responses, testing, and packaging.

Not notebook-only.

Depth Across LLM APIs and Agent Systems

Production experience with at least two of OpenAI, Anthropic Claude, Google Gemini, or open-weight models (vLLM, Ollama, Together).

Production experience with at least one agent framework (LangGraph, CrewAI, AutoGen, LlamaIndex Agents) or hand-rolled equivalent.

Hands-on with tool calling, structured outputs, and multi-step reasoning.

Demonstrated, Systematic Evaluation Practice - Non-Negotiable

Must have built evaluation harnesses that gate production releases, not ad-hoc testing.

Hands-on with at least one of LangSmith, Langfuse, Promptfoo, Ragas, or DeepEval.

Candidates with no systematic answer to evaluation should not be considered at senior level regardless of other strengths.

Cost Discipline for Production AI

Track record of measurable cost optimisation on production AI features.

Able to speak in specifics: cost per request, savings achieved through caching or model routing, context reduction decisions.

AWS Working Knowledge

Hands-on with EC2, S3, IAM, and Docker.

Comfort with CI/CD workflows and deploying AI services.

Awareness of LLM Security Failure Modes

Familiar with prompt injection patterns, understands that system prompt rules alone are insufficient, and has experience with output validation and content safety in production.

Nice to Have

• Experience with AST/tree-sitter tooling, diff-based editing systems, or compiler-adjacent work
• MCP server authoring
• Open-source AI contributions
• Published technical writing on LLM systems
• Multi-modal model experience
• Fine-tuning exposure (LoRA, QLoRA, PEFT)

Hiring for AI Engineer

Exp: 4 - 8 yrs

Edu : BE/B.Tech/MCA

Work Location : Pune

Skill Set

Large language,Artificial Intelligence,Machine Learning

- 4–7 years of experience in software engineering/AI roles

- Strong programming skills in Python or TypeScript (Java/Go is a plus)

- Hands-on experience with LLMs, RAG pipelines, and AI frameworks

- Experience building APIs and working with distributed systems

- Familiarity with Kubernetes, Docker, and CI/CD pipelines

- Experience with cloud platforms (AWS/Azure/GCP)

Excellent communication

Senior Agentic AI Engineer - (Freelance)

Positions: 2

Experience: Ideally 4(J–(J8 years with strong software-engineering fundamentals and recent hands-on Agentic AI experience.

Mission

Build UC2's governed AI agents capable of reasoning across and interacting safely with enterprise IT systems.

Mandatory capabilities

• Python
• LangGraph
• Agentic AI
• Tool/function calling
• Stateful workflows
• Structured outputs
• Human-in-the-loop
• Guardrails
• Agent state/checkpointing
• Agent evaluation
• FastAPI
• REST APIs
• Async Python

Retry/timeout/error handling

Highly desirable

MCP, LangChain, Semantic Kernel, agent observability, event-driven architecture and experience integrating AI agents with ServiceNow/Splunk/Confluence or similar enterprise platforms.

The candidate should understand how to engineer:

Location: Hyderabad, India. Based at the KnackLabs headquarters, with occasional travel to client locations for workshops and reviews. This role does not involve extended onsite deployments.

About the Role

You will work as an AI Architect who designs the systems behind our client engagements: AI agents, RAG systems, automation platforms, and the conventional backend systems around them.

This is a hands-on design role, not a slideware role. You will scope architectures with clients, make the hard technical decisions, defend them in review, and stay accountable for how the systems perform in production.

You will work directly with clients. Everyone at KnackLabs does. You will sit in design discussions with client engineering teams, present architecture decisions to technical and business stakeholders, and answer for the choices you make.

A full KnackLabs engineering team in Hyderabad builds with you. You own the technical design and the quality of what ships.

What you'll own

1. Architecture - Design AI agents, RAG systems, integrations, and the scalable backend systems around them, for multiple client engagements.
2. Technical scoping - Work directly with clients to turn a business problem into a system design, with clear trade-offs and clear reasons.
3. Scale and reliability - Make sure what we build handles real load: data stores, queues, caching, horizontal scaling, and fault tolerance.
4. Design reviews - Review designs and builds across engagements. Set the technical bar and hold it.
5. Evaluation strategy - Define how we measure accuracy, safety, latency, and cost for the AI systems we ship.
6. Guiding engineers - Raise the level of the engineers building with you, through reviews and direct pairing.
7. Feedback to the platform - Feed what you learn across engagements back into our platform and internal tools.

What we are looking for

1. Around 7 or more years of software engineering experience, including direct work with customers on design or delivery.
2. Full-stack development experience with strength in backend technologies.
3. Experience designing and building scalable applications. You understand how large-scale distributed systems work: data partitioning, queues, caching, horizontal scaling, and fault tolerance.
4. At least 2 years of strong, hands-on AI experience with large language models in production.
5. You build with AI coding tools like Claude Code or Codex as your default way of working. You understand Claude Skills, have written skills yourself, use them actively, and have contributed to them.
6. Hands-on experience building retrieval-augmented generation (RAG) systems: chunking, embeddings, vector databases, retrieval, and reranking.
7. Hands-on experience building AI agents.
8. Strong programming skills in Python. Working knowledge of TypeScript or JavaScript.
9. Experience with at least one cloud platform (AWS, Azure, or GCP).
10. Clear communication. You can explain an architecture decision to an engineer and to a business leader, and defend it under questioning.
11. High ownership and comfort with ambiguity. You can take an unclear problem and turn it into a design.

Nice to have

1. Experience building evaluations to measure accuracy, safety, latency, and cost.
2. Experience with observability and tracing tools such as LangSmith or Braintrust.
3. Experience with on-premises or private cloud (VPC) deployments.
4. Experience deploying AI systems in regulated industries such as insurance, banking, or the public sector.
5. Experience with data engineering and pipelines.
6. A history of side projects, open source contributions, or products you shipped end-to-end.
7. Experience working at a consulting or professional services firm in a client-facing delivery role.

Stack and tools

1. Languages: Python and TypeScript.
2. Models: Claude and other frontier or open-source models, chosen to fit the customer.
3. AI patterns: RAG, agents, prompt engineering, skills, and evaluations.
4. Vector and retrieval: vector databases and retrieval pipelines.
5. Cloud: AWS, Azure, or GCP, on public or private cloud.
6. Integration: REST APIs and enterprise system connectors.

Strong AI Engineer / Machine Learning Engineer profiles.

2

Mandatory (Experience 1) – Must have minimum 3+ years of hands-on experience in Data Science, Machine Learning, Applied AI, NLP, Deep Learning, or Generative AI solutions.

3

Mandatory (Experience 2) – Must have strong hands-on experience in Python programming, SQL, data analysis, feature engineering, model development, and production-grade ML applications.

4

Mandatory (Experience 3) – Must have experience working with Machine Learning and Deep Learning frameworks such as PyTorch, TensorFlow, Keras, Scikit-learn, or equivalent.

5

Mandatory (Experience 4) – Must have hands-on experience working on NLP, embeddings, semantic search, text classification, document understanding, recommendation systems, or similar AI/ML use cases.

6

Mandatory (Experience 5) – Must have experience working with Large Language Models (LLMs) such as GPT, Llama, Mistral, Claude, Gemini, Phi, or similar foundation models.

7

Mandatory (Experience 6) – Must have hands-on experience building or implementing RAG (Retrieval Augmented Generation) systems, vector search, knowledge retrieval, embeddings, chunking, indexing, or semantic retrieval solutions.

8

Mandatory (Experience 7) – Must have experience working with Git, CI/CD practices, production environments, and scalable AI/ML systems.

9

Mandatory (CTC) – The CTC breakup offered will be 75% fixed + 25% variable, as per company policy.

10

Mandatory (Age) - Candidate's Age should be below 30 Years

11

Preferred (Experience 1) – Experience with MLFlow, Kubeflow, Airflow, Prefect, Feature Stores, Model Registry, or MLOps/LLMOps frameworks.

12

Preferred (Experience 2) – Experience working with Vector Databases, Spark, PySpark, distributed ML pipelines, large-scale data processing, or real-time ML systems..

13

Preferred (Experience 3) – Familiarity with Docker, Kubernetes, Azure, AWS, GCP, cloud-native AI deployments, and scalable ML architecture.

14

Preferred (Company) – Candidates from AI-first startups, Fintech, Banking, Lending, Fraud Analytics, Risk Analytics, Product Companies, SaaS organizations, or data-driven technology companies

15

Mandatory ( Pedigree) - B.TECH / M.TECH from Tier 1 Colleges (IIT's, NIT's, BITS) are Considered.

Strong AI Engineer / Machine Learning Engineer profiles.

2

Mandatory (Experience 1) – Must have minimum 3+ years of hands-on experience in Data Science, Machine Learning, Applied AI, NLP, Deep Learning, or Generative AI solutions.

3

Mandatory (Experience 2) – Must have strong hands-on experience in Python programming, SQL, data analysis, feature engineering, model development, and production-grade ML applications.

4

Mandatory (Experience 3) – Must have experience working with Machine Learning and Deep Learning frameworks such as PyTorch, TensorFlow, Keras, Scikit-learn, or equivalent.

5

Mandatory (Experience 4) – Must have hands-on experience working on NLP, embeddings, semantic search, text classification, document understanding, recommendation systems, or similar AI/ML use cases.

6

Mandatory (Experience 5) – Must have experience working with Large Language Models (LLMs) such as GPT, Llama, Mistral, Claude, Gemini, Phi, or similar foundation models.

7

Mandatory (Experience 6) – Must have hands-on experience building or implementing RAG (Retrieval Augmented Generation) systems, vector search, knowledge retrieval, embeddings, chunking, indexing, or semantic retrieval solutions.

8

Mandatory (Experience 7) – Must have experience working with Git, CI/CD practices, production environments, and scalable AI/ML systems.

9

Mandatory (CTC) – The CTC breakup offered will be 75% fixed + 25% variable, as per company policy.

10

Mandatory (Age) - Candidate's Age should be below 28 Years