{"id":2753208,"url":"https://alion.io/job/conga-ai-data-scientist","title":"AI Data Scientist","company":{"id":5652,"name":"Conga","domain":"conga.com","url":"https://alion.io/company/conga","size_band":"201-500","is_staffing_agency":false,"employer_type":"direct","is_intermediary":false,"listed_via":null,"ats_vendor":"Greenhouse","truth_index":{"grade":"B","score":80,"open_postings":5,"ghost_share":0,"stale_share":0.8,"repost_share":0,"time_to_fill_p50_days":45,"computed_at":"2026-10-17T05:46:00Z"}},"role":"AI/ML","role_family":"AI/ML","seniority":"staff","employment_type":null,"work_mode":"remote","remote_scope":"stated_countries","remote_scope_basis":"posting_text","remote_working_hours":null,"hiring_geo_confidence":"explicit","locations":["Houston, United States"],"countries":["US"],"hiring_countries":["CA"],"hiring_countries_total":1,"salary":null,"salary_estimate":{"min_usd":177000,"max_usd":328000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":157},"experience_years_min":10,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Embeddings","optional":false},{"name":"Fine-tuning","optional":false},{"name":"LLM","optional":false},{"name":"Machine Learning","optional":false},{"name":"NLP","optional":false},{"name":"RAG","optional":false},{"name":"Transformers","optional":false},{"name":"Agile","optional":true},{"name":"AI Agents","optional":true},{"name":"AWS","optional":true},{"name":"Azure","optional":true},{"name":"BigQuery","optional":true},{"name":"Databricks","optional":true},{"name":"Docker","optional":true},{"name":"DSPy","optional":true},{"name":"ElasticSearch","optional":true},{"name":"Encoder-Decoder","optional":true},{"name":"FAISS","optional":true},{"name":"GCP","optional":true},{"name":"Google BigQuery","optional":true},{"name":"Hugging Face","optional":true},{"name":"Knowledge Distillation","optional":true},{"name":"Knowledge Graph","optional":true},{"name":"Kubeflow","optional":true},{"name":"Kubernetes","optional":true},{"name":"LangChain","optional":true},{"name":"LlamaIndex","optional":true},{"name":"LoRA","optional":true},{"name":"Milvus","optional":true},{"name":"MLFlow","optional":true},{"name":"Model Distillation","optional":true},{"name":"Multimodal AI","optional":true},{"name":"NER","optional":true},{"name":"NLTK","optional":true},{"name":"OpenSearch","optional":true},{"name":"PEFT","optional":true},{"name":"Pinecone","optional":true},{"name":"Prompt Engineering","optional":true},{"name":"Python","optional":true},{"name":"PyTorch","optional":true},{"name":"QLoRA","optional":true},{"name":"Quantization","optional":true},{"name":"Ray","optional":true},{"name":"Reranking","optional":true},{"name":"Semantic Search","optional":true},{"name":"Semantic Search","optional":true},{"name":"Sentence-Transformers","optional":true},{"name":"spaCy","optional":true},{"name":"Spark","optional":true},{"name":"SQL","optional":true},{"name":"Synthetic Data","optional":true},{"name":"TensorFlow","optional":true},{"name":"Tokenization","optional":true},{"name":"Weaviate","optional":true}],"status":"live","first_seen_at":"2026-10-16T21:37:06Z","employer_posted_date":"2026-10-16","last_verified_at":"2026-10-17T11:21:29Z","board_verified":true,"closed_at":null,"days_open":0,"trust":{"level":"ok","repost_count":null,"flags":[],"days_open":0},"description":"A career that’s the whole package!\nAt Conga, we’ve built a community where our colleagues can thrive. Here you’ll find opportunities to innovate and support growth through individual and team development, all within an environment where every voice is heard.\nConga lines up commercial operations so companies run as connected, smarter businesses. By unifying the people and processes that drive commerce, Conga aligns pricing, quoting, contracting, rebates, and communications so teams stay in sync and buyers keep moving forward. The result is trusted decisions, consistent buyer experiences, and profitable growth. More than 10,000 customers worldwide, including over 50% of the Fortune 100®, trust Conga when commercial complexity is high and global impact is on the line.\nAI Data Scientist\nLocation: Houston - Hybrid, Canada - Remote\nReports to: Senior Director, Science | Platform AI - R&D\nA quick snapshot…\nAs an AI Data Scientist at Conga, you will be a hands-on technical leader responsible for researching, building, evaluating, and deploying the natural language and machine learning capabilities that power our revenue lifecycle management solutions. You will work across traditional NLP, statistical machine learning, deep learning, and Generative AI to solve complex product and business problems, partnering closely with Engineering, Product, and Data Science teams to take solutions from first experiment to production at scale.\nThis role is ideal for a scientist who pairs deep research instincts with a builder's mindset. You understand both the theory and the practical tradeoffs behind NLP and ML, and you know how to choose the right approach based on data, performance, latency, cost, and business need.\nWhy it's a big deal…\nAt Conga, AI is central to how we help customers make sense of their most complex commercial documents and decisions. Contracts, quotes, and agreements are rich with unstructured language, and turning that language into trusted insight is one of the biggest opportunities in front of us.\nAs an AI Data Scientist, you will help shape how Conga applies NLP and Generative AI across our platform. Your work will directly influence product intelligence, model quality, and the experience thousands of customers rely on every day. You'll also help raise the technical bar across the team through mentorship, rigorous evaluation standards, and a steady stream of applied research.\nYou'll work alongside a highly talented team of scientists and engineers dedicated to solving hard problems while supporting products that help customers streamline and transform their revenue operations.\nWhat you'll lead…\nApplied Research & Innovation\nResearch and evaluate emerging NLP, machine learning, deep learning, and Generative AI techniques, translating the most promising advances into practical solutions.\nInvestigate ambiguous technical problems independently, form hypotheses, and run experiments that compare competing approaches.\nContinuously evaluate new models, frameworks, and methodologies, adopting those with demonstrated potential to improve product capabilities and system performance.\nNLP & Machine Learning Development\nDesign and build traditional NLP, statistical ML, deep learning, and transformer-based solutions using the right algorithms, architectures, and representations for the problem.\nDevelop data pipelines, NLP preprocessing, feature representations, embeddings, and training datasets across structured and unstructured data.\nEstablish data-quality strategies that keep models reliable as data and use cases evolve.\nGenerative AI & LLM Solutions\nDevelop and evaluate LLM and GenAI solutions using prompting, RAG, embeddings, vector search, fine-tuning, agents, and structured generation.\nSelect and optimize models based on accuracy, latency, cost, and business requirements.\nHelp define how Conga builds, grounds, and governs GenAI capabilities across the platform.\nEvaluation & Experimentation Excellence\nDesign rigorous experiments, benchmarks, evaluation datasets, and statistical methodologies to measure and improve NLP, ML, and GenAI systems.\nLead error analysis and performance measurement that turn results into clear next steps.\nSet evaluation standards the broader team can adopt and build on.\nProduction & Operational Excellence\nTake NLP and AI solutions from research and prototype through production deployment, monitoring, and ongoing optimization.\nPartner with engineering teams to operationalize models at scale with strong reliability and performance.\nProactively identify model drift, quality gaps, and optimization opportunities in live systems.\nCross-Functional Partnership & Mentorship\nCollaborate with engineering, product, and data science teams to solve complex problems and shape technical direction.\nProvide technical guidance and mentorship in NLP, ML, experimentation, and GenAI.\nFoster a culture of curiosity, scientific rigor, and continuous learning.\nAre you the person we're looking for?\nMaster's degree in Computer Science, Data Science, Computational Linguistics, Statistics, Mathematics, Engineering, or a related quantitative field. Ph.D. preferred but not required.\n10+ years of professional experience in data science, machine learning, NLP, or AI, including significant hands-on experience building and deploying NLP and/or GenAI solutions.\nProven experience taking ML, NLP, or GenAI solutions from experimentation through production deployment and ongoing optimization.\nDemonstrated ability to translate open-ended research into practical, measurable outcomes.\nExcellent communication skills and a track record of working effectively as a senior individual contributor across technical teams.\nTechnical Expertise\nExpert-level Python with extensive use of Hugging Face Transformers, spaCy, NLTK, Sentence Transformers, PyTorch, and TensorFlow.\nExpert knowledge of traditional NLP, including tokenization, stemming, lemmatization, n-grams, TF-IDF, topic modeling, text classification, named entity recognition, information extraction, semantic similarity, and information retrieval.\nStrong understanding of deep learning architectures, including CNNs, RNNs, LSTMs, GRUs, encoder-decoder models, attention mechanisms, and Transformers.\nStrong understanding of Transformer-based language models, including embeddings, pretraining, fine-tuning, and inference.\nHands-on experience with LLMs and foundation models, including prompt engineering, RAG, vector search, reranking, fine-tuning, LoRA/QLoRA, structured generation, and LLM evaluation.\nStrong grasp of experimental design, statistical testing, cross-validation, hyperparameter optimization, and error analysis.\nExperience with NLP and GenAI evaluation metrics, including precision, recall, F1, ROC-AUC, MAP, MRR, NDCG, semantic similarity, groundedness, and relevance.\nStrong SQL skills and experience with structured and unstructured data at scale.\nExperience with distributed data processing platforms such as Spark, Databricks, or BigQuery.\nExperience with cloud platforms such as Databricks, GCP, AWS, or Azure and modern ML infrastructure.\nExperience with ML tooling such as MLflow, Kubeflow, Weights & Biases, Docker, Kubernetes, or Ray.\nExperience with vector databases and search technologies such as FAISS, Elasticsearch/OpenSearch, Pinecone, Weaviate, or Milvus.\nFamiliarity with LLM application frameworks such as LangChain, LlamaIndex, or DSPy.\nKey Competencies\nResearch Depth\nYou bring strong theoretical foundations and the curiosity to explore new techniques, while staying grounded in what will actually move the product forward.\nBuilder's Mindset\nYou enjoy getting hands-on, turning prototypes into production systems, and owning outcomes well past the first experiment.\nScientific Rigor\nYou hold yourself and your team to high standards for evaluation, measurement, and evidence-based decisions.\nCollaboration & Communication\nYou partner effectively across functions and explain complex technical concepts clearly to diverse audiences.\nTechnical Leadership\nYou elevate those around you through mentorship, thoughtful guidance, and sound technical judgment.\nHere's what will give you an edge…\nExperience with NLP in the legal domain, such as NER, document classification, or semantic search over legal documents.\nExperience with advanced information retrieval, semantic search, document intelligence, multimodal models, or knowledge graphs.\nExperience with parameter-efficient fine-tuning, model quantization, distillation, inference optimization, synthetic data generation, and agentic architectures.\nAdvanced knowledge of cloud AI/ML platforms and distributed training and inference for large-scale LLM systems.\nContributions to the field through publications, patents, open-source projects, conference talks, or technical writing.\nExperience working within Agile, cross-functional product development teams.\nTravel\nLimited travel to other Conga offices upon request.\nDid we pique your interest? \nIf this sounds like the kind of job you would love in the kind of environment where you would thrive, please click apply. We'd love to hear from you!\nPreferred Resume Format \nWe accept resumes in any format, we suggest using PDF or plain text. These formats help ensure that your resume’s formatting remains intact, making it easier for our recruiters to review your application promptly. \nDon’t meet every requirement for the role? \nStudies have shown that women and members of ethnic minorities are less likely to apply to jobs unless they meet every single qualification. At Conga we are dedicated to building a diverse, inclusive, and authentic workplace, so if you’re excited about this role but your experience doesn’t align perfectly with every qualification in the job description, we encourage you to apply anyway. You just might be the right candidate for this or other roles. \nAdditional Information\nConga is proud to be an Equal Opportunity Employer and provides equal employment opportunities to all employees and applicants regardless of race, color, religion, gender, gender identity, age, national origin, disability, parental or pregnancy status, marriage and civil partnership, sexual orientation, veteran status, or any other characteristic protected by law. We understand interviewing can be stressful for those with disabilities. If reasonable accommodation is needed to allow you to show us your best self, please let your recruiter know as soon as possible. All your information will be kept confidential according to EEO guidelines. Conga is not open to third party solicitation or resumes for our posted FTE positions. Resumes received from third party agencies that are unsolicited will be considered complimentary.\nConga's Applicant Privacy Statement \nThe information you provide during the application process will be used in accordance with Conga’s Applicant Privacy Statement (https://conga.com/applicant-privacy-statement). By submitting your application, you acknowledge and agree to the terms outlined in this privacy statement.","description_format":"text","description_chars":11029,"description_truncated":false,"requirements":{"experience_years_min":10,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":{"level":"master","optional":false},"security_clearance":false,"languages":[]},"benefits":["Continuous learning"],"hiring_locations":[{"name":"Canada","iso":"CA","kind":"country"}],"hiring_excludes":[],"relocation_offered":false,"industries":["CRM Software","Workflow & Process Automation (RPA, BPM)","Legal Software"],"lifecycle":[{"event":"open","at":"2026-10-17T00:47:30Z"}],"visa":[{"country":"US","licensed_sponsor":true,"evidence":"H-1B filings in 12 months: 35 · green card filings: 2","filings_12m":35,"filings_prev_12m":14,"green_card_filings_12m":2,"median_offered_wage_usd":162230,"route":null,"cap_exempt":false,"checked_at":"2026-10-15T11:24:14+00:00","sources":["US Department of Labor: LCA disclosure data (H-1B, H-1B1, E-3)","US Department of Labor: PERM disclosure data (green cards)"],"filings_for_role_12m":14}],"liveness":{"score":86,"band":"hot","label":"Hiring now","p_open":1,"p_active":0.86,"p_room":1,"age_days":0,"expected_fill_days":45,"reasons":["conf:0","win:early"],"computed_at":"2026-10-17T05:46:00Z"},"pay":null,"html_url":"https://alion.io/job/conga-ai-data-scientist","json_url":"https://alion.io/job/conga-ai-data-scientist.json","meta":{"generated_at":"2026-10-17T13:28:14Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","about":"Alion is a live layer of people, companies and AI agents: who they are, whether they are real and active right now, what they do and how to work with them, readable by people and by agents and paid per call.","catalog":"https://alion.io/catalog.json","usage":{"tier":"crawler_verified","counted_by":"address","units_charged":1,"used_today":18101,"day_limit":null,"remaining_today":null,"minute_limit":300,"resets_at":"2026-10-18T00:00:00Z"}},"offers":[{"id":"company.slices","title":"One company in depth, by slice","status":"live","price":{"credits":0.02,"usd":0.002,"plus_per_slice":{"credits":0.05,"usd":0.005}},"unit":"per company, plus each slice with data","note":"the employer in depth","call":{"mcp_tool":"get_company","arguments":{"id":5652},"rest":"https://alion.io/mcp/rest/get_company?id=5652"},"human":"https://alion.io/catalog?offer=company.slices&for=job%2Fconga-ai-data-scientist"},{"id":"market.stats","title":"A market slice: pay, demand and time to fill","status":"live","price":{"credits":1,"usd":0.1},"unit":"per slice","note":"pay, demand and time to fill for this role and place","call":{"mcp_tool":"market_stats"},"human":"https://alion.io/catalog?offer=market.stats&for=job%2Fconga-ai-data-scientist"},{"id":"job.search","title":"Open jobs by role, technology, place, pay and visa","status":"live","price":{"credits":0.02,"usd":0.002},"unit":"per posting in a list","note":"similar open postings","call":{"mcp_tool":"search_jobs"},"human":"https://alion.io/catalog?offer=job.search&for=job%2Fconga-ai-data-scientist"},{"id":"company.verify","title":"Is this company real and active right now","status":"pilot","price":null,"unit":"per company","request":{"url":"https://alion.io/catalog/request","method":"POST","body":"{\"offer\": \"company.verify\", \"for\": \"job/conga-ai-data-scientist\", \"note\": \"what you need it for\"}"},"human":"https://alion.io/catalog?offer=company.verify&for=job%2Fconga-ai-data-scientist"}]}