Applied AI Engineer — Memory & Context Systems (Aiva)

aivarinnovations· R&D
Apply Now ↗
📍 Coimbatore, TN, IndiaFULL TIME

About this role

You will build the intelligence layer of Aiva: the LLM-powered pipelines that turn raw agent interactions into structured, durable memory — and decide what an agent should remember, consolidate, retrieve, or forget. Where the retrieval engineer makes memory fast, you make it smart. You will work daily with Claude on Bedrock, and with Kubogent-fine-tuned small models where latency and cost demand them, and you will own the evaluation harnesses that prove memory quality actually improves agent outcomes.

Key Responsibilities
  • Build memory extraction pipelines: turning conversations, documents, and process events into structured facts, entities, relationships, and episodic summaries using LLMs (Claude on Bedrock) and NLP techniques.
  • Design and implement memory consolidation: merging duplicate or conflicting facts, progressive summarization of long histories, salience scoring, and decay/forgetting policies.
  • Develop context assembly logic: given an agent task and token budget, select, rank, and compress the right memories into the prompt — balancing relevance, recency, and cost.
  • Build the Aiva evaluation stack: retrieval-quality benchmarks (precision/recall of remembered facts), memory-drift and contamination tests, hallucination checks, and A/B measurement of downstream agent task success.
  • Prototype and productionize embedding strategies: model selection, chunking, hybrid sparse+dense representations, and re-ranking.
  • Partner with the Kubogent team to fine-tune and deploy small models for high-volume memory tasks (extraction, classification, summarization) where frontier-model calls are too slow or costly.
  • Instrument PII detection and redaction in memory pipelines, working within AI Gateway/ReVAct governance policies.
  • Stay current with memory-architecture research (episodic/semantic memory, GraphRAG, agentic memory frameworks) and translate it into shipped capability.
Must-Have Qualifications
  • 4+ years of software engineering with strong Python, including 2+ years building LLM or NLP applications in production.
  • Hands-on experience with prompt engineering, structured output extraction, RAG pipelines, and embedding models — beyond demos, with real users and real failure modes.
  • Experience building evaluation frameworks for LLM systems: golden datasets, LLM-as-judge patterns, regression suites, and offline/online metric design.
  • Solid ML fundamentals: retrieval metrics, ranking, classification, and enough statistics to design and interpret A/B tests.
  • Working knowledge of AWS ML stack (Bedrock, SageMaker) or equivalent cloud ML platforms.
  • Strong software craftsmanship: testing, versioning of prompts/models/datasets, and reproducible pipelines.
Nice-to-Have
  • Experience fine-tuning small/open models (LoRA/QLoRA, distillation) and serving them efficiently.
  • Familiarity with agent memory frameworks and research (e.g., GraphRAG, MemGPT-style architectures, reflection/consolidation patterns).
  • Knowledge-graph construction experience: NER, relation extraction, entity linking.
  • Multilingual NLP experience relevant to Indian enterprise customers (Hindi, Tamil, and other Indic languages).
  • Published work, open-source contributions, or strong writing on applied LLM systems.
Shared: Why Join Aivar
  • Zero-to-one ownership of the platform layer that differentiates Aivar's entire accelerator suite — memory is the moat.
  • Founded by four ex-AWS/Amazon executives; backed by Bessemer Venture Partners and Sorin Investments; AWS Preferred Partner building on Anthropic/Claude foundations.
  • Your work ships into large regulated enterprises across telecom, BFSI, healthcare, and manufacturing — at production scale, not proofs of concept.
  • Small, senior team with direct access to founders and customers; competitive compensation with meaningful ESOPs.

Frequently Asked Questions

Is the salary disclosed for the Applied AI Engineer — Memory & Context Systems (Aiva) position at aivarinnovations?
The salary for this Applied AI Engineer — Memory & Context Systems (Aiva) role at aivarinnovations is not publicly listed. Click "Apply Now" to learn more about the compensation package on their official careers page.
Where is the Applied AI Engineer — Memory & Context Systems (Aiva) position at aivarinnovations located?
This Applied AI Engineer — Memory & Context Systems (Aiva) role at aivarinnovations is based in Coimbatore, TN, India. The position is listed as on-site or hybrid. Check the full job description or apply directly to confirm the work arrangement.
Is the Applied AI Engineer — Memory & Context Systems (Aiva) role at aivarinnovations full-time or part-time?
This is listed as a FULL TIME position. It is posted as a Applied AI Engineer — Memory & Context Systems (Aiva) role in the R&D department at aivarinnovations.
Which team or department does the Applied AI Engineer — Memory & Context Systems (Aiva) at aivarinnovations belong to?
This Applied AI Engineer — Memory & Context Systems (Aiva) position is part of the R&D department at aivarinnovations. See the full job description for more information about the team structure and responsibilities.
How do I apply for the Applied AI Engineer — Memory & Context Systems (Aiva) position at aivarinnovations?
Click the "Apply Now" button on this page. You will be redirected to aivarinnovations's official application portal hosted on keka where you can submit your application directly.
When was the Applied AI Engineer — Memory & Context Systems (Aiva) job at aivarinnovations posted?
This Applied AI Engineer — Memory & Context Systems (Aiva) position at aivarinnovations was posted on Sep 23, 2026. Apply as soon as possible — early applications are often reviewed first.
Applied AI Engineer — Memory & Context Systems (Aiva)
aivarinnovations
Apply for this role ↗

You'll be redirected to aivarinnovations's official application page on keka.